Triple
T27087681
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | 28th Dáil |
E686078
|
entity |
| Predicate | termStartUnderPresident |
P87685
|
FINISHED |
| Object | Mary McAleese |
—
|
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: Mary McAleese | Statement: [28th Dáil, termStartUnderPresident, Mary McAleese]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: termStartUnderPresident Context triple: [28th Dáil, termStartUnderPresident, Mary McAleese]
-
A.
presidentTermStart
Indicates the date or point in time when an individual officially begins serving as president of an entity.
-
B.
presidentAtStartOfTerm
Indicates that the subject was the president holding office at the beginning of the specified term or period.
-
C.
termAsActingPresidentStart
Indicates the date or point in time when an individual begins serving in the role of acting president.
-
D.
beganDuringPresidencyOf
chosen
Indicates that an event, process, or state started while a specified person was serving as president.
-
E.
presidentSince
Indicates that one entity has held the office of president of another entity starting from a specified point in time.
- 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_69ef148940ec819097b5c20fbfbf7c81 |
completed | April 27, 2026, 7:47 a.m. |
| NER | Named-entity recognition | batch_69f63fd6c68481908c542aa03e297b9c |
completed | May 2, 2026, 6:17 p.m. |
| PD | Predicate disambiguation | batch_69f63c663be481908f233d25d28713a4 |
completed | May 2, 2026, 6:03 p.m. |
Created at: April 27, 2026, 8:38 a.m.