Triple
T29313890
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | New York City legal community |
E743324
|
entity |
| Predicate | includesLawSchool |
P79124
|
FINISHED |
| Object | Columbia Law School |
—
|
NE NERFINISHED |
How this triple was built (2 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: Columbia Law School | Statement: [New York City legal community, includesLawSchool, Columbia Law School]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: includesLawSchool Context triple: [New York City legal community, includesLawSchool, Columbia Law School]
-
A.
containsLawSchool
chosen
Indicates that one entity includes or encompasses a law school as part of its structure, contents, or composition.
-
B.
lawSchoolCanon
Indicates that one entity is a canonical or widely recognized law school attended or associated with the other entity.
-
C.
lawSchoolName
Indicates the name of the law school with which an entity (such as a person or institution) is associated.
-
D.
lawSchoolRankingContext
Indicates the contextual ranking information associated with a law school, such as its position or status within a specified ranking system or timeframe.
-
E.
legalSchoolPractice
Indicates that a particular legal practice, method, or approach is characteristic of, endorsed by, or derived from a specific school or tradition of law.
- F. None of above.
Provenance (3 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_69f0912502c8819087d9e8398ee991a8 |
completed | April 28, 2026, 10:51 a.m. |
| NER | Named-entity recognition | batch_69ffacdf9f5c8190baef0245edfe87fc |
completed | May 9, 2026, 9:53 p.m. |
| PD | Predicate disambiguation | batch_69ffac5e86e08190a1e6da0840a237ad |
completed | May 9, 2026, 9:51 p.m. |
Created at: April 28, 2026, 1:18 p.m.