Triple
T35297103
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | murder of Johnny Boz |
E1019401
|
entity |
| Predicate | portrayedInPerformanceByVictimActor |
P199605
|
FINISHED |
| Object | Bill Cable |
—
|
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: Bill Cable | Statement: [murder of Johnny Boz, portrayedInPerformanceByVictimActor, Bill Cable]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: portrayedInPerformanceByVictimActor Context triple: [murder of Johnny Boz, portrayedInPerformanceByVictimActor, Bill Cable]
-
A.
portraysAsVictim
Indicates that one entity represents or depicts another entity as a victim in a given context or narrative.
-
B.
performedForCharacterPortrayedBy
Indicates that an action or performance was carried out for the benefit of a fictional character as portrayed by a specific actor.
-
C.
accusedCharacterPortrayedBy
Indicates that a particular actor or performer plays the role of the character who is accused within a given work.
-
D.
portraysActorAs
Indicates that one entity depicts or represents an actor in a particular role, character, or manner.
-
E.
usedByActorPortrayingCharacter
Indicates that something (such as an item, prop, or element) is used by the actor while portraying a specific character.
- F. None of above. chosen
Provenance (4 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_69f76de7eedc8190a3bdc64ebbc05b42 |
completed | May 3, 2026, 3:46 p.m. |
| NER | Named-entity recognition | batch_69ff48199b1c8190bb05872f8a4f4673 |
completed | May 9, 2026, 2:43 p.m. |
| PD | Predicate disambiguation | batch_69ff4746b1cc8190854f70a124df7d04 |
completed | May 9, 2026, 2:40 p.m. |
| PDg | Predicate description generation | batch_69ff4818bb288190b4a27576fad18e23 |
completed | May 9, 2026, 2:43 p.m. |
Created at: May 3, 2026, 4:03 p.m.