Triple
T38029673
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | 1991 Haitian coup d’état |
E948871
|
entity |
| Predicate | restoredLeader |
P189971
|
FINISHED |
| Object | Jean-Bertrand Aristide |
—
|
NE NERFINISHED |
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: Jean-Bertrand Aristide | Statement: [1991 Haitian coup d’état, restoredLeader, Jean-Bertrand Aristide]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: restoredLeader Context triple: [1991 Haitian coup d’état, restoredLeader, Jean-Bertrand Aristide]
-
A.
promotedLeader
Indicates that one entity has elevated another entity to a higher leadership position or role.
-
B.
removedLeader
Indicates that one entity has taken action to depose, dismiss, or otherwise remove another entity from a position of leadership or authority.
-
C.
capturedLeader
Indicates that one party has taken control of and detained the primary leader of another group or entity.
-
D.
laterLeader
Indicates that one entity serves as a leader or holds a leadership role at a later time than another specified leader.
-
E.
establishedUnderLeader
Indicates that an entity was founded, created, or formally established during the tenure or authority of a specific leader.
- F. None of above. chosen
Provenance (4 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_69f76efd1bc48190a729097fe5177b61 |
completed | May 3, 2026, 3:51 p.m. |
| NER | Named-entity recognition | batch_69fc4748843c8190931432653be4890c |
completed | May 7, 2026, 8:03 a.m. |
| PD | Predicate disambiguation | batch_69fc45646ce481908caf292ff9f06e15 |
completed | May 7, 2026, 7:55 a.m. |
| PDg | Predicate description generation | batch_69fc4747b06c8190a3ea5331f02eedad |
completed | May 7, 2026, 8:03 a.m. |
Created at: May 3, 2026, 4:20 p.m.