Triple
T20432481
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Andrés de Santa Cruz |
E501165
|
entity |
| Predicate | officeStart (President of South Peru) |
P8144
|
FINISHED |
| Object | 1836 |
—
|
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: 1836 | Statement: [Andrés de Santa Cruz, officeStart (President of South Peru), 1836]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: officeStart (President of South Peru) Context triple: [Andrés de Santa Cruz, officeStart (President of South Peru), 1836]
-
A.
officeStartForPresident
chosen
Indicates the date or point in time when a person begins serving in the role of president.
-
B.
officeStartTime (President of Mexico)
Indicates the time at which the President of Mexico officially begins their term in office.
-
C.
officeStart (Chairman of State Council)
Indicates the date or point in time when an individual began serving as Chairman of the State Council.
-
D.
officeStartAsViceroyOfRíoDeLaPlata
Indicates the time or event when someone begins serving in the office of Viceroy of the Río de la Plata.
-
E.
commanderForPeru
Indicates that an entity serves or has served as a military commander on behalf of Peru.
- 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_69e0b4ab3cfc8190ac9bf32e932316b1 |
completed | April 16, 2026, 10:06 a.m. |
| NER | Named-entity recognition | batch_69e685eba35881908c316443b6d789fb |
completed | April 20, 2026, 8 p.m. |
| PD | Predicate disambiguation | batch_69e5766df0008190a73c4f613c29678f |
completed | April 20, 2026, 12:42 a.m. |
Created at: April 16, 2026, 11:31 a.m.