Triple
T30016686
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Maccabees |
E762614
|
entity |
| Predicate | universityPresidentDuringRecentSuccess |
P169344
|
FINISHED |
| Object | Ari Berman |
—
|
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: Ari Berman | Statement: [Maccabees, universityPresidentDuringRecentSuccess, Ari Berman]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: universityPresidentDuringRecentSuccess Context triple: [Maccabees, universityPresidentDuringRecentSuccess, Ari Berman]
-
A.
foundingChancellor
Indicates that a person served as the first (original) chancellor at the founding of an institution or organization.
-
B.
hasViceChancellor
Indicates that one entity serves as the vice chancellor of another entity.
-
C.
servedAsViceChancellorUntil
Indicates that an individual held the position of vice chancellor up to a specified end date or time period.
-
D.
endTime (President of the University of Waterloo)
Indicates the date and time at which a person’s term as President of the University of Waterloo concludes.
-
E.
rectorOrPresident
Indicates that one entity serves as the rector or president (i.e., the chief executive or head) of another entity, typically an institution such as a university.
- 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_69f2246b0c84819094f1250b6a02d277 |
completed | April 29, 2026, 3:31 p.m. |
| NER | Named-entity recognition | batch_69f67de7792c81909b5e4e812d143624 |
completed | May 2, 2026, 10:42 p.m. |
| PD | Predicate disambiguation | batch_69f678ce54b081908c26edfd49e39c60 |
completed | May 2, 2026, 10:21 p.m. |
| PDg | Predicate description generation | batch_69f67d31cc60819084f64bd056e1ea4d |
completed | May 2, 2026, 10:39 p.m. |
Created at: April 29, 2026, 6:46 p.m.