Triple
T28270253
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Torch Song |
E712825
|
entity |
| Predicate | leadActressVocalDubbing |
P115423
|
FINISHED |
| Object | India Adams for Joan Crawford |
—
|
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: India Adams for Joan Crawford | Statement: [Torch Song, leadActressVocalDubbing, India Adams for Joan Crawford]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: leadActressVocalDubbing Context triple: [Torch Song, leadActressVocalDubbing, India Adams for Joan Crawford]
-
A.
leadActorAlsoVoices
Indicates that the lead actor in a production also provides the voice for a character, typically in an animated or voice-over role.
-
B.
voiceActorFemale
Indicates that the subject is a female voice actor who provides the voice for the specified character or role.
-
C.
leadActress
Indicates that the subject is the primary female performer in the specified film, show, or production.
-
D.
hasVoiceActing
Indicates that one entity provides voice performance for a character, role, or work associated with another entity.
-
E.
voiceActorOfPerformer
chosen
Indicates that one performer provides the voice for a character or role portrayed by another performer.
- 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_69efb5216c6881908020dce4aea65381 |
completed | April 27, 2026, 7:12 p.m. |
| NER | Named-entity recognition | batch_69f65f7731e4819099d5bd3d915ee266 |
completed | May 2, 2026, 8:32 p.m. |
| PD | Predicate disambiguation | batch_69f65c2198208190a3954086c22cfcbf |
completed | May 2, 2026, 8:18 p.m. |
Created at: April 27, 2026, 11:17 p.m.