Triple
T9340077
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Isidore Newman School |
E224740
|
entity |
| Predicate | collegePreparation |
P87610
|
FINISHED |
| Object | offers Advanced Placement courses |
—
|
LITERAL FINISHED |
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: offers Advanced Placement courses | Statement: [Isidore Newman School, collegePreparation, offers Advanced Placement courses]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: collegePreparation Context triple: [Isidore Newman School, collegePreparation, offers Advanced Placement courses]
-
A.
collegeCoach
Indicates that one entity serves as a coach for a college-level sports team associated with another entity.
-
B.
collegeAchievement
Indicates that an entity has attained a specific level of success, recognition, or accomplishment in a college or higher-education context.
-
C.
college
Indicates that an entity is a college-level educational institution attended by or associated with another entity.
-
D.
collegeLevel
Indicates the academic level or year of study a person has reached within a college or university program.
-
E.
nearCollege
Indicates that one entity is located close to or in the vicinity of a college.
- F. None of above. chosen
Provenance (4 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_69ca84286fcc81909f6e7fd7a7e862a2 |
completed | March 30, 2026, 2:09 p.m. |
| NER | Named-entity recognition | batch_69cd4bae2e2481909effc2dc89a642c5 |
completed | April 1, 2026, 4:45 p.m. |
| PD | Predicate disambiguation | batch_69cc7a66aef08190b8d668cff5b04f5f |
completed | April 1, 2026, 1:52 a.m. |
| PDg | Predicate description generation | batch_69cc94b796788190816b71b1e9996288 |
completed | April 1, 2026, 3:44 a.m. |
Created at: March 30, 2026, 7:40 p.m.