Triple
T22103573
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Mademoiselle Lanoire |
E546228
|
entity |
| Predicate | characterRoleRelatedTo |
P23263
|
FINISHED |
| Object | central female character |
—
|
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: central female character | Statement: [Mademoiselle Lanoire, characterRoleRelatedTo, central female character]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: characterRoleRelatedTo Context triple: [Mademoiselle Lanoire, characterRoleRelatedTo, central female character]
-
A.
featuresCharacterRole
chosen
Indicates that a work includes a character appearing in a specific narrative or functional role.
-
B.
relationshipRoleInFilm
Indicates that one entity has a specific relationship-based role (e.g., spouse, sibling, partner) to another entity within the context of a particular film.
-
C.
relatedCharacter
Indicates that one character has a specified relationship or association with another character.
-
D.
characterPortrayedIs
Indicates that one entity serves as the fictional or dramatic role that is depicted or played by another entity.
-
E.
associatedWithCharacterRole
Indicates that one entity has a connection or linkage to a specific character role played or held by another entity.
- 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_69e11e378dc08190896d6a51597afd5a |
completed | April 16, 2026, 5:36 p.m. |
| NER | Named-entity recognition | batch_69f129175a7881909549883f23c53dca |
completed | April 28, 2026, 9:39 p.m. |
| PD | Predicate disambiguation | batch_69e71b20ec50819096ac196c798f8e3c |
completed | April 21, 2026, 6:37 a.m. |
Created at: April 16, 2026, 8:30 p.m.