Triple
T35828017
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Frank Pentangeli |
E1035705
|
entity |
| Predicate | testifiesAbout |
P164343
|
FINISHED |
| Object | Michael Corleone’s criminal activities |
—
|
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: Michael Corleone’s criminal activities | Statement: [Frank Pentangeli, testifiesAbout, Michael Corleone’s criminal activities]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: testifiesAbout Context triple: [Frank Pentangeli, testifiesAbout, Michael Corleone’s criminal activities]
-
A.
gaveTestimonyIn
Indicates that one entity provided formal testimony or a statement in an official proceeding, event, or context associated with another entity.
-
B.
testimonyAffects
Indicates that one party’s testimony has an influence or impact on another entity, situation, or outcome.
-
C.
hasTestimony
Indicates that an entity provides, contains, or is associated with a formal statement or account (testimony) about another entity or event.
-
D.
testimonyCharacteristic
Indicates that a particular quality, feature, or attribute is being ascribed to a testimony or statement given by an entity.
-
E.
testimonyTopic
chosen
Indicates that the content or subject matter of a given testimony is about a specified topic.
- 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_69f76e192a94819082db360cb91e6a8d |
completed | May 3, 2026, 3:47 p.m. |
| NER | Named-entity recognition | batch_69f7aa699d68819081ed363931894ab3 |
completed | May 3, 2026, 8:04 p.m. |
| PD | Predicate disambiguation | batch_69f7a8d219f8819081dc4ce3c83ca0cb |
completed | May 3, 2026, 7:58 p.m. |
Created at: May 3, 2026, 4:06 p.m.