Triple
T31723676
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Golpe de Estado de 1955 en Argentina |
E809650
|
entity |
| Predicate | líderGolpista |
P50317
|
FINISHED |
| Object | Eduardo Lonardi |
—
|
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: Eduardo Lonardi | Statement: [Golpe de Estado de 1955 en Argentina, líderGolpista, Eduardo Lonardi]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: líderGolpista Context triple: [Golpe de Estado de 1955 en Argentina, líderGolpista, Eduardo Lonardi]
-
A.
coupLeader
chosen
Indicates that the subject is the primary organizer or head figure responsible for leading a coup against an existing authority.
-
B.
coupLeaderOpposedBy
Indicates that the identified coup leader is actively resisted, challenged, or opposed by another specified party.
-
C.
belligerentLeader
Indicates that an entity serves as a leader or authority figure of a party engaged in a conflict, war, or hostile confrontation.
-
D.
politicalLeaderBehind
Indicates that a political leader is the driving force or primary influence behind a particular action, decision, policy, or event.
-
E.
coupParticipantIn
Indicates that an entity took part in, contributed to, or was involved in carrying out a specific coup event.
- 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_69f348e009c8819095d77df52c645b9c |
completed | April 30, 2026, 12:19 p.m. |
| NER | Named-entity recognition | batch_69f6aafa2a1481909ecc84df0624c2b9 |
completed | May 3, 2026, 1:55 a.m. |
| PD | Predicate disambiguation | batch_69f6aa20a1588190a53533fc9764efb2 |
completed | May 3, 2026, 1:51 a.m. |
Created at: April 30, 2026, 11:19 p.m.