Triple
T4082910
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Mr. Bernstein |
E87518
|
entity |
| Predicate | filmCharacterType |
P23263
|
FINISHED |
| Object | Kane’s trusted employee |
—
|
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: Kane’s trusted employee | Statement: [Mr. Bernstein, filmCharacterType, Kane’s trusted employee]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: filmCharacterType Context triple: [Mr. Bernstein, filmCharacterType, Kane’s trusted employee]
-
A.
featuresCharacterRole
chosen
Indicates that a work includes a character appearing in a specific narrative or functional role.
-
B.
characterIn
Indicates that an entity appears as a character within a specified work, story, or narrative.
-
C.
featuresCharactersFrom
Indicates that one entity (such as a work or production) includes or presents characters originating from another entity.
-
D.
notableCharacterType
Indicates that an entity is a notable or prominent example of a specified character type or role.
-
E.
actingRoleType
Indicates the specific type or category of role an entity performs when acting in a particular capacity or function.
- 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_69aed9435cf48190ad1da737c962d19d |
completed | March 9, 2026, 2:29 p.m. |
| NER | Named-entity recognition | batch_69aefc7933b481909bb3e02c6c04c8ee |
completed | March 9, 2026, 4:59 p.m. |
| PD | Predicate disambiguation | batch_69aef9082c2081908474f082a49bebc8 |
completed | March 9, 2026, 4:44 p.m. |
Created at: March 9, 2026, 3:39 p.m.