Triple
T18852022
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Andrés Manuel López Obrador |
E461062
|
entity |
| Predicate | officeStartForPresidentOfMexico |
P8144
|
FINISHED |
| Object | 2018-12-01 |
—
|
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: 2018-12-01 | Statement: [Andrés Manuel López Obrador, officeStartForPresidentOfMexico, 2018-12-01]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: officeStartForPresidentOfMexico Context triple: [Andrés Manuel López Obrador, officeStartForPresidentOfMexico, 2018-12-01]
-
A.
officeStartTime (President of Mexico)
Indicates the time at which the President of Mexico officially begins their term in office.
-
B.
officeStartForPresident
chosen
Indicates the date or point in time when a person begins serving in the role of president.
-
C.
officeEndTime (President of Mexico)
Indicates the time at which a President of Mexico’s term in office concludes.
-
D.
officeStartTime (Vice President of the United States)
Indicates the date and time at which a person begins serving in the role of Vice President of the United States.
-
E.
officeAssumedAsPresidentFollowing
Indicates that one entity assumed the office of president immediately after another entity, in a direct succession.
- 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_69d8dcfa11e4819090ab1ef5bdcd2b2e |
completed | April 10, 2026, 11:20 a.m. |
| NER | Named-entity recognition | batch_69e5c05995e88190b189864fcbda68e5 |
completed | April 20, 2026, 5:57 a.m. |
| PD | Predicate disambiguation | batch_69e48d1e7dac81909ea1e758c87773c5 |
completed | April 19, 2026, 8:06 a.m. |
Created at: April 10, 2026, 11:56 a.m.