Triple
T198563
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Fidel Castro |
E4050
|
entity |
| Predicate | officeEndForFirstSecretary |
P2941
|
FINISHED |
| Object | 2011-04-19 |
—
|
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: 2011-04-19 | Statement: [Fidel Castro, officeEndForFirstSecretary, 2011-04-19]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: officeEndForFirstSecretary Context triple: [Fidel Castro, officeEndForFirstSecretary, 2011-04-19]
-
A.
officeEnded
chosen
Indicates that a person’s term in an office or position has concluded at a specified time or under certain conditions.
-
B.
leftOffice
Indicates that an entity ceased holding or performing the duties of a particular office or position.
-
C.
officeStart
Indicates the time or date at which an entity’s term, role, or period of holding office begins.
-
D.
serviceSecretary
Indicates that one entity serves in the role of secretary for another entity.
-
E.
officeInvolved
Indicates that a particular office or organizational unit is involved or participates in a specified event, action, or relationship.
- 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_69a254bca59881909a15e1496f1508c7 |
completed | Feb. 28, 2026, 2:36 a.m. |
| NER | Named-entity recognition | batch_69a25be47ea881909c296b30a0d47a65 |
completed | Feb. 28, 2026, 3:07 a.m. |
| PD | Predicate disambiguation | batch_69a25b47481c8190add47c641c977bb9 |
completed | Feb. 28, 2026, 3:04 a.m. |
Created at: Feb. 28, 2026, 2:44 a.m.