Triple
T15832728
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Michel Temer |
E383909
|
entity |
| Predicate | presidentOfChamberStart |
P89217
|
FINISHED |
| Object | 1997 |
—
|
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: 1997 | Statement: [Michel Temer, presidentOfChamberStart, 1997]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: presidentOfChamberStart Context triple: [Michel Temer, presidentOfChamberStart, 1997]
-
A.
legislatureStartPresidentOfChamber
chosen
Indicates that this person began serving as the president (presiding officer) of a legislative chamber at the start of a specified legislative term.
-
B.
currentChairStartDate
Indicates the date on which the person’s current term as chair officially began.
-
C.
lastCommissionerOrPresident
Indicates that the subject is the most recent individual to have served as commissioner or president of the specified organization or body.
-
D.
chairpersonStart
Indicates the time or event at which a person begins serving as the chairperson of an organization or group.
-
E.
hasChairHolder
Indicates that an entity holds or occupies a specific chair position or role associated with another entity.
- 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_69d86da34c888190976e06c4019d415a |
completed | April 10, 2026, 3:25 a.m. |
| NER | Named-entity recognition | batch_69e11e653e388190a4696cdb22546715 |
completed | April 16, 2026, 5:37 p.m. |
| PD | Predicate disambiguation | batch_69e005418f588190824d91ff7974dada |
completed | April 15, 2026, 9:38 p.m. |
Created at: April 10, 2026, 4:49 a.m.