Triple
T30078514
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Sherlock Holmes and the Spider Woman |
E764390
|
entity |
| Predicate | portraysAntagonist |
P116420
|
FINISHED |
| Object | Gale Sondergaard |
—
|
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: Gale Sondergaard | Statement: [Sherlock Holmes and the Spider Woman, portraysAntagonist, Gale Sondergaard]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: portraysAntagonist Context triple: [Sherlock Holmes and the Spider Woman, portraysAntagonist, Gale Sondergaard]
-
A.
portraysAdversary
Indicates that one entity depicts or represents another entity as an opponent, enemy, or rival.
-
B.
antagonistActorRole
chosen
Indicates that an actor plays the role of an antagonist in a given work or context.
-
C.
antagonistEmbodiment
Indicates that one entity serves as the personification or concrete manifestation of an antagonistic force, role, or concept in relation to another entity.
-
D.
mainAntagonistPortrayedBy
Indicates that the person is the primary actor who plays the main antagonist character in a work.
-
E.
hasAntagonisticProtagonist
Indicates that the work features a main character who opposes or undermines the typical heroic or moral expectations of a traditional protagonist.
- 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_69f22472eee081909791dc372aa766e9 |
completed | April 29, 2026, 3:32 p.m. |
| NER | Named-entity recognition | batch_69fd57ba740c8190bd1d40166fccccb7 |
completed | May 8, 2026, 3:25 a.m. |
| PD | Predicate disambiguation | batch_69fd55ee82b881908a639da3a41b3af6 |
completed | May 8, 2026, 3:18 a.m. |
Created at: April 29, 2026, 7:02 p.m.