Triple
T360841
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Town of Yorktown |
E7846
|
entity |
| Predicate | partOfWatershed |
P5506
|
FINISHED |
| Object |
Croton Watershed
The Croton Watershed is a major New York City water supply watershed in the lower Hudson Valley, encompassing numerous reservoirs and tributaries that provide drinking water to the city and surrounding communities.
|
E1836
|
NE FINISHED |
How this triple was built (5 steps)
Every LLM step that produced this triple, in pipeline order — named-entity classification, the disambiguation choices (the exact options shown, with the pick highlighted), and the generated description. The batch + timestamp of each is in the Provenance table below.
NER
Named-entity recognition
gpt-5-mini
Instruction
Given a phrase, classify it is english named entity (e.g., persons, organizations, works of art) in Latin script, or not (e.g., literals, dates, URLs, verbose phrases). For disambiguation, the statement where the phrase occurs as object is also given. Please return a JSON object with `phrase` (string, the phrase being analyzed) and `is_ne` (boolean, indicating whether the phrase is a Named Entity).
Input
Phrase: Croton Watershed | Statement: [Town of Yorktown, partOfWatershed, Croton Watershed]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Croton Watershed Context triple: [Town of Yorktown, partOfWatershed, Croton Watershed]
-
A.
Bull Run watershed
The Bull Run watershed is a drainage basin in northern Virginia whose streams and rivers, including Bull Run, shape the local hydrology and landscape around communities such as Manassas.
-
B.
Mystic River watershed
The Mystic River watershed is a drainage basin in the Greater Boston area of Massachusetts that collects water from numerous rivers and streams before emptying into Boston Harbor.
-
C.
Don River
The Don River is a significant waterway in Toronto, Ontario, that flows south through the city into Lake Ontario and has played an important role in its urban and environmental history.
-
D.
San Tomas Aquino Creek
San Tomas Aquino Creek is a small urban waterway in Santa Clara County, California, that flows through several cities in Silicon Valley before emptying into the southern end of San Francisco Bay.
-
E.
Croton River
The Croton River is a river in southeastern New York that flows through Westchester and Putnam counties and is a key source for New York City's Croton water supply system.
- F. None of above. chosen
- G. Unsure - the case is ambiguous/there is not enough information to decide.
NEDg
Description generation
gpt-5.1
Instruction
Generate a one-sentence description of the target entity. You are given a context triple in the form (subject, predicate, object), where the object is the target entity. # Instructions Use the triple to infer relevant information about the entity. Describe the entity based on what is most defining, well-known. Avoid repeating the information from the triple, unless really essential. # Response Format Return only the sentence: "Description: [one-sentence description of the target entity]"
Input
Entity: Croton Watershed Triple: [Town of Yorktown, partOfWatershed, Croton Watershed]
Generated description
The Croton Watershed is a major New York City water supply watershed in the lower Hudson Valley, encompassing numerous reservoirs and tributaries that provide drinking water to the city and surrounding communities.
NED2
Entity disambiguation (via description)
gpt-5-mini-2025-08-07
Target entity: Croton Watershed Target entity description: The Croton Watershed is a major New York City water supply watershed in the lower Hudson Valley, encompassing numerous reservoirs and tributaries that provide drinking water to the city and surrounding communities.
-
A.
Bull Run watershed
The Bull Run watershed is a drainage basin in northern Virginia whose streams and rivers, including Bull Run, shape the local hydrology and landscape around communities such as Manassas.
-
B.
Mystic River watershed
The Mystic River watershed is a drainage basin in the Greater Boston area of Massachusetts that collects water from numerous rivers and streams before emptying into Boston Harbor.
-
C.
Don River
The Don River is a significant waterway in Toronto, Ontario, that flows south through the city into Lake Ontario and has played an important role in its urban and environmental history.
-
D.
San Tomas Aquino Creek
San Tomas Aquino Creek is a small urban waterway in Santa Clara County, California, that flows through several cities in Silicon Valley before emptying into the southern end of San Francisco Bay.
-
E.
Croton River
chosen
The Croton River is a river in southeastern New York that flows through Westchester and Putnam counties and is a key source for New York City's Croton water supply system.
- F. None of above.
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: partOfWatershed Context triple: [Town of Yorktown, partOfWatershed, Croton Watershed]
-
A.
hydrologicallyLocatedIn
Indicates that a water-related feature (such as a river, lake, or watershed) is situated within or associated with a specific geographic or administrative area in terms of hydrology.
-
B.
drainageBasin
Indicates the area of land where all precipitation and surface water flow are collected and drained toward a particular river, lake, or other water body.
-
C.
basin
chosen
Indicates a geographic area where surface water drains into a common outlet, such as a river, lake, or ocean.
-
D.
basinType
Indicates the specific kind or classification of a basin associated with an entity (e.g., by form, function, or hydrological role).
-
E.
tributary
Indicates that one watercourse flows into and feeds another, contributing its water to a larger stream, river, or lake.
- F. None of above.
Provenance (6 batches)
The batch behind each pipeline step, in order, with when it ran. Timestamps are batch-level — stages were processed in waves, so the object chain (NER → NED1 → NEDg → NED2) reads in order, but predicate / elicitation batches can sit in a different wave.
| Step | Stage | Batch ID | Status | When |
|---|---|---|---|---|
| creating | Elicitation | batch_69a2e7e880008190a6ad7e06e5d03007 |
completed | Feb. 28, 2026, 1:04 p.m. |
| NER | Named-entity recognition | batch_69a2ebccb8d88190a31f7c443a0c8566 |
completed | Feb. 28, 2026, 1:21 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69a79277143c819091019a9ca625039f |
completed | March 4, 2026, 2:01 a.m. |
| NEDg | Description generation | batch_69a7931d1bac8190b9b300f3d7f94131 |
completed | March 4, 2026, 2:04 a.m. |
| NED2 | Entity disambiguation (via description) | batch_69a793860a688190a537418beb72141c |
completed | March 4, 2026, 2:05 a.m. |
| PD | Predicate disambiguation | batch_69a2e95aeed48190b5e48865cc964938 |
completed | Feb. 28, 2026, 1:10 p.m. |
Created at: Feb. 28, 2026, 1:08 p.m.