Triple
T28588376
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Fieschi assassination attempt |
E723571
|
entity |
| Predicate | perpetratorCaptured |
P75957
|
FINISHED |
| Object | Giuseppe Marco Fieschi |
—
|
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: Giuseppe Marco Fieschi | Statement: [Fieschi assassination attempt, perpetratorCaptured, Giuseppe Marco Fieschi]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: perpetratorCaptured Context triple: [Fieschi assassination attempt, perpetratorCaptured, Giuseppe Marco Fieschi]
-
A.
perpetratorAccordingToConviction
Indicates that an entity is identified as the perpetrator of an offense according to a formal legal conviction.
-
B.
perpetratorState
Indicates the state, condition, or status of the entity that carries out or is responsible for a particular harmful, illegal, or wrongful act.
-
C.
perpetratorDeath
Indicates that the referenced individual is the one who caused or is responsible for another entity’s death.
-
D.
perpetratorTrial
Indicates that a legal trial is conducted to judge the actions or guilt of the identified perpetrator.
-
E.
prisonerOf
chosen
Indicates that one entity is held in custody or confinement by another entity, typically under legal or authoritative control.
- 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_69f01d7f92e481909847f5f3f3174a89 |
completed | April 28, 2026, 2:37 a.m. |
| NER | Named-entity recognition | batch_69f652a492108190b885b955ce147d3c |
completed | May 2, 2026, 7:38 p.m. |
| PD | Predicate disambiguation | batch_69f651aad92c8190b874b3b5f9f64434 |
completed | May 2, 2026, 7:34 p.m. |
Created at: April 28, 2026, 4:19 a.m.