Triple
T23962362
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Mayor of Jerusalem |
E603961
|
entity |
| Predicate | notableFormerOfficeHolder |
P59478
|
FINISHED |
| Object | Teddy Kollek |
—
|
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: Teddy Kollek | Statement: [Mayor of Jerusalem, notableFormerOfficeHolder, Teddy Kollek]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: notableFormerOfficeHolder Context triple: [Mayor of Jerusalem, notableFormerOfficeHolder, Teddy Kollek]
-
A.
notableFormerOfficeHolderRole
chosen
Indicates that an entity previously held a particular official position or role that is considered notable.
-
B.
notableOfficeHolder
Indicates that an entity is a significant or distinguished holder of a particular office or position associated with another entity.
-
C.
notablePolitician
Indicates that the subject is a politician who is recognized as notable or significant in a political context.
-
D.
notableFormerHolderRole
Indicates that an entity previously held a particular notable role or position.
-
E.
notableFormerLeader
Indicates that the subject was once a leader of the object and is recognized as particularly significant or prominent in that former leadership role.
- 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_69e2954222288190a7323554d0cca8d7 |
completed | April 17, 2026, 8:17 p.m. |
| NER | Named-entity recognition | batch_69f1d0db90c88190adc18e9ee107281b |
completed | April 29, 2026, 9:35 a.m. |
| PD | Predicate disambiguation | batch_69f161578d54819084a8b35496299993 |
completed | April 29, 2026, 1:39 a.m. |
Created at: April 17, 2026, 9:23 p.m.