Triple
T27246649
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Micheál Martin |
E687362
|
entity |
| Predicate | precededInPartyLeadershipBy |
P34201
|
FINISHED |
| Object | Brian Cowen |
—
|
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: Brian Cowen | Statement: [Micheál Martin, precededInPartyLeadershipBy, Brian Cowen]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: precededInPartyLeadershipBy Context triple: [Micheál Martin, precededInPartyLeadershipBy, Brian Cowen]
-
A.
precededAsMinorityLeaderBy
Indicates that one individual previously served as minority leader and was directly succeeded in that role by another individual.
-
B.
precededInSenateBy
Indicates that one officeholder directly held a given Senate seat before another officeholder, in terms of succession to that seat.
-
C.
precededAsVicePresidentBy
Indicates that one entity served as vice president immediately before another entity in a sequence of officeholders.
-
D.
predecessorInOffice
chosen
Indicates that one officeholder directly held a particular position before another officeholder in an official succession.
-
E.
precededByOfficeHolder
Indicates that one office holder directly held a position before another office holder in a sequence of occupants of the same office.
- 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_69ef355547408190b5ca0d777c65040a |
completed | April 27, 2026, 10:07 a.m. |
| NER | Named-entity recognition | batch_69f69383222c81909d8baa04129d5c81 |
completed | May 3, 2026, 12:14 a.m. |
| PD | Predicate disambiguation | batch_69f690eb1e948190aab41a89969519a5 |
completed | May 3, 2026, 12:03 a.m. |
Created at: April 27, 2026, 10:42 a.m.