Triple
T31723689
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Golpe de Estado de 1955 en Argentina |
E809650
|
entity |
| Predicate | precedidoPor |
P25144
|
FINISHED |
| Object | Bombardeo de Plaza de Mayo de 1955 |
—
|
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: Bombardeo de Plaza de Mayo de 1955 | Statement: [Golpe de Estado de 1955 en Argentina, precedidoPor, Bombardeo de Plaza de Mayo de 1955]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: precedidoPor Context triple: [Golpe de Estado de 1955 en Argentina, precedidoPor, Bombardeo de Plaza de Mayo de 1955]
-
A.
usedToPrecede
Indicates that one entity regularly or habitually came before another in time or sequence in the past.
-
B.
classPrecededBy
Indicates that one class occurs or is scheduled before another class in a sequence or timetable.
-
C.
precededByInPosition
Indicates that one entity occurs or appears immediately before another entity in a specific ordered position or sequence.
-
D.
wasPrecededBy
chosen
Indicates that one event, state, or entity occurred or existed earlier in time than another.
-
E.
precedesDisc
Indicates that one discourse segment or unit occurs before another in the sequence of discourse.
- 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_69f7cec454a88190a9f3bbee2b856636 |
completed | May 3, 2026, 10:40 p.m. |
| PD | Predicate disambiguation | batch_69f7c8977c288190997a892ec5f756ed |
completed | May 3, 2026, 10:13 p.m. |
Created at: April 30, 2026, 11:19 p.m.