Triple
T23723500
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Brown University school functions |
E586207
|
entity |
| Predicate | mayOccurAt |
P24433
|
FINISHED |
| Object | Brown University athletic facilities |
—
|
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: Brown University athletic facilities | Statement: [Brown University school functions, mayOccurAt, Brown University athletic facilities]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: mayOccurAt Context triple: [Brown University school functions, mayOccurAt, Brown University athletic facilities]
-
A.
occursAt
chosen
Indicates that an event or action takes place at a specific time or location.
-
B.
occursFor
Indicates that an event, process, or condition takes place in relation to, or on behalf of, a particular entity or context.
-
C.
mayAlsoBeCalled
Indicates that one entity can alternatively be referred to by another name or label.
-
D.
mayAppear
Indicates that an entity is allowed or has the possibility to be present or occur in association with another entity or context.
-
E.
occursTo
Indicates that an event, idea, or realization happens in or comes to the mind or awareness of an entity.
- 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_69e24906fb108190a6898751e46bdc11 |
completed | April 17, 2026, 2:51 p.m. |
| NER | Named-entity recognition | batch_69f1b91364208190b3404534a7403e08 |
completed | April 29, 2026, 7:53 a.m. |
| PD | Predicate disambiguation | batch_69f155e4b1148190836ede4741dcb888 |
completed | April 29, 2026, 12:50 a.m. |
Created at: April 17, 2026, 7:07 p.m.