Triple
T27190562
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Tony Green |
E683462
|
entity |
| Predicate | voicedFor |
P55263
|
FINISHED |
| Object | Marvel Comics |
—
|
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: Marvel Comics | Statement: [Tony Green, voicedFor, Marvel Comics]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: voicedFor Context triple: [Tony Green, voicedFor, Marvel Comics]
-
A.
hasVoicing
Indicates that one sound, segment, or phoneme is characterized by the presence or absence of vocal fold vibration (voicing) in relation to another or to a specified voicing property.
-
B.
hasVoiceIn
chosen
Indicates that an entity participates by providing a voice role or vocal performance in another entity, such as a work, production, or recording.
-
C.
hasVoices
Indicates that an entity possesses or includes one or more vocal parts, voice tracks, or spoken/sung voice elements.
-
D.
hasVoiceActing
Indicates that one entity provides voice performance for a character, role, or work associated with another entity.
-
E.
speaksFor
Indicates that one entity expresses views, decisions, or positions on behalf of 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_69eefad140408190b8586fdebcf9af46 |
completed | April 27, 2026, 5:57 a.m. |
| NER | Named-entity recognition | batch_69f625abb50081908345dd4cff9fee49 |
completed | May 2, 2026, 4:26 p.m. |
| PD | Predicate disambiguation | batch_69f620e38aec8190bb184edcdbd6da64 |
completed | May 2, 2026, 4:05 p.m. |
Created at: April 27, 2026, 9:32 a.m.