Triple
T1070622
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Frank Costello |
E23317
|
entity |
| Predicate | resultOfAssassinationAttempt |
P6158
|
FINISHED |
| Object | wounded but survived |
—
|
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: wounded but survived | Statement: [Frank Costello, resultOfAssassinationAttempt, wounded but survived]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: resultOfAssassinationAttempt Context triple: [Frank Costello, resultOfAssassinationAttempt, wounded but survived]
-
A.
assassinationAttemptLocation
Indicates the place where an attempted assassination occurred or was intended to occur.
-
B.
relatedAssassination
chosen
Indicates a relationship where one entity is connected to, involved in, or associated with an assassination event concerning another entity.
-
C.
assassinationDate
Indicates the date on which an assassination of the referenced entity occurred.
-
D.
attemptedCoup
Indicates that an entity tried, but did not necessarily succeed, to overthrow an existing government or leadership through a coup.
-
E.
killedBy
Indicates that one entity caused the death of another entity.
- 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_69a493ee1f908190992b5f0d1b04459b |
completed | March 1, 2026, 7:30 p.m. |
| NER | Named-entity recognition | batch_69a4b92848148190ba8795cb8d0a1d0a |
completed | March 1, 2026, 10:09 p.m. |
| PD | Predicate disambiguation | batch_69a4b73844708190a16c9e9824ca2fb6 |
completed | March 1, 2026, 10:01 p.m. |
Created at: March 1, 2026, 7:42 p.m.