Triple
T12436480
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | 1981 French presidential election |
E297155
|
entity |
| Predicate | hasFirstRoundDate |
P47097
|
FINISHED |
| Object | 1981-04-26 |
—
|
LITERAL FINISHED |
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: 1981-04-26 | Statement: [1981 French presidential election, hasFirstRoundDate, 1981-04-26]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: hasFirstRoundDate Context triple: [1981 French presidential election, hasFirstRoundDate, 1981-04-26]
-
A.
firstRoundDate
chosen
Indicates the date on which the first round of an event, process, or competition takes place.
-
B.
hasPreliminaryRounds
Indicates that an event, competition, or process includes one or more initial qualifying rounds before the main or final stage.
-
C.
firstRoundEndDate
Indicates the date on which the first round of an event, process, or competition concludes.
-
D.
hasRound
Indicates that an entity possesses, includes, or is associated with a particular round (e.g., a round of an event, game, or process).
-
E.
hasQualifyingRounds
Indicates that an event or competition includes preliminary qualifying rounds that participants must complete before advancing further.
- 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_69d6ada0640c81908c061d7fb3d47786 |
completed | April 8, 2026, 7:33 p.m. |
| NER | Named-entity recognition | batch_69d94df948308190ace333230a4a3b38 |
completed | April 10, 2026, 7:22 p.m. |
| PD | Predicate disambiguation | batch_69d94d391c548190996a8c698357f273 |
completed | April 10, 2026, 7:19 p.m. |
Created at: April 8, 2026, 9:55 p.m.