Triple
T2843009
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Yadkin River |
E62512
|
entity |
| Predicate | hasTributary |
P415
|
FINISHED |
| Object |
Dutchmans Creek
Dutchmans Creek is a smaller stream in North Carolina that feeds into the Yadkin River as one of its tributaries.
|
E525024
|
NE FINISHED |
How this triple was built (4 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: Dutchmans Creek | Statement: [Yadkin River, hasTributary, Dutchmans Creek]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Dutchmans Creek Context triple: [Yadkin River, hasTributary, Dutchmans Creek]
-
A.
Gerritsen Creek
Gerritsen Creek is a tidal creek in Brooklyn, New York, that runs through Marine Park and is known for its salt marshes and role in local urban ecology.
-
B.
Highland Creek
Highland Creek is a residential neighbourhood in the eastern Toronto district of Scarborough, known for its ravine landscapes and proximity to the University of Toronto Scarborough campus.
-
C.
Woods Creek
Woods Creek is a small waterway in Tuolumne County, California, known for flowing through the historic Gold Rush town of Jamestown.
-
D.
Kings Creek
Kings Creek is a stream known for feeding the scenic Kings Creek Falls, a popular natural attraction.
-
E.
Hunting Creek
Hunting Creek is a smaller stream in North Carolina that feeds into the Yadkin River as one of its tributaries.
- 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: Dutchmans Creek Triple: [Yadkin River, hasTributary, Dutchmans Creek]
Generated description
Dutchmans Creek is a smaller stream in North Carolina that feeds into the Yadkin River as one of its tributaries.
NED2
Entity disambiguation (via description)
gpt-5-mini-2025-08-07
Target entity: Dutchmans Creek Target entity description: Dutchmans Creek is a smaller stream in North Carolina that feeds into the Yadkin River as one of its tributaries.
-
A.
Gerritsen Creek
Gerritsen Creek is a tidal creek in Brooklyn, New York, that runs through Marine Park and is known for its salt marshes and role in local urban ecology.
-
B.
Highland Creek
Highland Creek is a residential neighbourhood in the eastern Toronto district of Scarborough, known for its ravine landscapes and proximity to the University of Toronto Scarborough campus.
-
C.
Woods Creek
Woods Creek is a small waterway in Tuolumne County, California, known for flowing through the historic Gold Rush town of Jamestown.
-
D.
Kings Creek
Kings Creek is a stream known for feeding the scenic Kings Creek Falls, a popular natural attraction.
-
E.
Hunting Creek
chosen
Hunting Creek is a smaller stream in North Carolina that feeds into the Yadkin River as one of its tributaries.
- F. None of above.
Provenance (5 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_69ab4c3d16bc81908b3a1c98fbd287fe |
completed | March 6, 2026, 9:50 p.m. |
| NER | Named-entity recognition | batch_69abdf1898748190b031a2bd2091c0c0 |
completed | March 7, 2026, 8:17 a.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69bf856d4d6481908b99610cf52abc76 |
completed | March 22, 2026, 6 a.m. |
| NEDg | Description generation | batch_69bf8632767c8190bdb5c4f6a505169e |
completed | March 22, 2026, 6:03 a.m. |
| NED2 | Entity disambiguation (via description) | batch_69bf86ab7b988190953cff2d4387f742 |
completed | March 22, 2026, 6:05 a.m. |
Created at: March 6, 2026, 10:01 p.m.