Triple
T31153124
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | San Francisco Community College Board of Trustees members |
E794132
|
entity |
| Predicate | holdMeetingsIn |
P13127
|
FINISHED |
| Object | San Francisco |
—
|
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: San Francisco | Statement: [San Francisco Community College Board of Trustees members, holdMeetingsIn, San Francisco]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: holdMeetingsIn Context triple: [San Francisco Community College Board of Trustees members, holdMeetingsIn, San Francisco]
-
A.
meetingsAre
Indicates that certain entities function as or are classified as meetings in relation to one another.
-
B.
hasMeetings
Indicates that an entity participates in or is associated with one or more scheduled meetings.
-
C.
hasMeeting
chosen
Indicates that one entity is scheduled to participate in or hold a meeting with another entity or at a specific time or place.
-
D.
convenesDuring
Indicates that one entity formally gathers or brings together another entity or group during a specified time period or event.
-
E.
meetingsWere
Indicates that one or more meetings occurred or were held between the referenced entities.
- 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_69f224d41bb48190a5621cd1485e3a30 |
completed | April 29, 2026, 3:33 p.m. |
| NER | Named-entity recognition | batch_69f69dfdda708190be290c7bec205445 |
completed | May 3, 2026, 12:59 a.m. |
| PD | Predicate disambiguation | batch_69f69d1a37e081908d1d86b90ff502bd |
completed | May 3, 2026, 12:55 a.m. |
Created at: April 29, 2026, 9:06 p.m.