Triple
T16866283
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | James Gandolfini as Eddie Poole |
E410045
|
entity |
| Predicate | onScreenPersonaType |
P87723
|
FINISHED |
| Object | bullyEnforcer |
—
|
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: bullyEnforcer | Statement: [James Gandolfini as Eddie Poole, onScreenPersonaType, bullyEnforcer]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: onScreenPersonaType Context triple: [James Gandolfini as Eddie Poole, onScreenPersonaType, bullyEnforcer]
-
A.
stagePersonaOf
Indicates a relationship where one entity is the staged or performed persona, role, or character representation of another entity.
-
B.
portrayedByCharacterType
chosen
Indicates that an entity is depicted or represented by a character of a specified type (e.g., hero, villain, sidekick) in a narrative or media work.
-
C.
hasPersona
Indicates that an entity possesses or is associated with a particular persona, role, or character profile.
-
D.
mediaAppearanceType
Indicates the specific kind or category of media appearance associated with an entity (e.g., interview, feature, cameo, or performance).
-
E.
appliesToPersonType
Indicates that something (such as a rule, condition, or attribute) is relevant or applicable specifically to a certain type or category of person.
- 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_69d88395e6c88190b22730f335107c14 |
completed | April 10, 2026, 4:59 a.m. |
| NER | Named-entity recognition | batch_69e3b5088f208190abfe937633ebe3fe |
completed | April 18, 2026, 4:44 p.m. |
| PD | Predicate disambiguation | batch_69e32b8cbb048190878a259cc5be960e |
completed | April 18, 2026, 6:58 a.m. |
Created at: April 10, 2026, 5:24 a.m.