Triple
T31961947
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Highlands, New York |
E816062
|
entity |
| Predicate | postalNameIncludes |
P58620
|
FINISHED |
| Object |
Highland Falls
Highland Falls is a small village in Orange County, New York, located near the United States Military Academy at West Point along the Hudson River.
|
E1985367
|
NE FINISHED |
How this triple was built (3 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: Highland Falls | Statement: [Highlands, New York, postalNameIncludes, Highland Falls]
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: Highland Falls Triple: [Highlands, New York, postalNameIncludes, Highland Falls]
Generated description
Highland Falls is a small village in Orange County, New York, located near the United States Military Academy at West Point along the Hudson River.
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: postalNameIncludes Context triple: [Highlands, New York, postalNameIncludes, Highland Falls]
-
A.
postalName
chosen
Indicates the standardized name or label used for addressing and postal purposes associated with an entity.
-
B.
postalAreaIncludes
Indicates that a given postal area geographically contains or covers another specified location or region.
-
C.
hasPostalCodePrefix
Indicates that a location’s postal code begins with a specified sequence of characters.
-
D.
postalRegionOf
Indicates that a given area or zone serves as the designated postal region for another location or address.
-
E.
postalArea
Indicates that one entity is the postal or ZIP code area associated with the location or address represented by the other entity.
- 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_69f348f4ec708190abbb2a7c3ed58844 |
completed | April 30, 2026, 12:20 p.m. |
| NER | Named-entity recognition | batch_69f6b2e75b088190a60bdfba81feef44 |
completed | May 3, 2026, 2:28 a.m. |
| NED1 | Entity disambiguation (via context triple) | batch_6a2e8a5398588190bee382af4c3a1644 |
completed | June 14, 2026, 11:02 a.m. |
| NEDg | Description generation | batch_6a2e8af50dc08190bbc5f3e04528b335 |
completed | June 14, 2026, 11:05 a.m. |
| NED2 | Entity disambiguation (via description) | batch_6a2ea6a967dc8190af1d4e84ed34013b |
completed | June 14, 2026, 1:03 p.m. |
| PD | Predicate disambiguation | batch_69f6b151ad008190836c1bcdec503ce2 |
completed | May 3, 2026, 2:22 a.m. |
Created at: May 1, 2026, 12:09 a.m.