Triple
T38570068
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Cleaver |
E929239
|
entity |
| Predicate | containsCharacterParallel |
P132767
|
FINISHED |
| Object | boss character modeled on Tony Soprano |
—
|
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: boss character modeled on Tony Soprano | Statement: [Cleaver, containsCharacterParallel, boss character modeled on Tony Soprano]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: containsCharacterParallel Context triple: [Cleaver, containsCharacterParallel, boss character modeled on Tony Soprano]
-
A.
containsCharacter
Indicates that one entity includes a specific character as part of its content or composition.
-
B.
containsCharacterAction
Indicates that an entity includes or features an action performed by a character within it.
-
C.
parallelCharacter
chosen
Indicates that one character corresponds to or mirrors another character in a parallel role, function, or narrative pattern.
-
D.
hasRecurringCharacterFrom
Indicates that one work or series includes a character who also appears recurrently in another work or series.
-
E.
hasCharacterSequence
Indicates that one entity contains, exhibits, or follows a specific ordered sequence of characters.
- 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_69f76ebd2248819083978362d81fa35e |
completed | May 3, 2026, 3:50 p.m. |
| NER | Named-entity recognition | batch_6a0227ce59a081909fe1ba1181d86b4d |
completed | May 11, 2026, 7:02 p.m. |
| PD | Predicate disambiguation | batch_6a02273989208190beb948b8c7bdaee3 |
completed | May 11, 2026, 7 p.m. |
Created at: May 3, 2026, 4:32 p.m.