Triple
T28566775
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Debbie Wolowitz |
E722699
|
entity |
| Predicate | voiceHeardFrom |
P84907
|
FINISHED |
| Object | off-screen |
—
|
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: off-screen | Statement: [Debbie Wolowitz, voiceHeardFrom, off-screen]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: voiceHeardFrom Context triple: [Debbie Wolowitz, voiceHeardFrom, off-screen]
-
A.
hearsFrom
Indicates that one entity receives information, communication, or a message from another entity.
-
B.
heardBy
chosen
Indicates that a sound, message, or communication produced by one entity is perceived or received auditorily by another entity.
-
C.
canHear
Indicates that one entity is able to perceive sounds produced by another entity.
-
D.
hasVoiceIn
Indicates that an entity participates by providing a voice role or vocal performance in another entity, such as a work, production, or recording.
-
E.
lastKnownSpeaker
Indicates the entity that was most recently identified or recorded as speaking in a given context or interaction.
- 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_69f01a5f69d08190ad5c0d2167078dec |
completed | April 28, 2026, 2:24 a.m. |
| NER | Named-entity recognition | batch_69f674e06c9481909ed0ea736408f0d7 |
completed | May 2, 2026, 10:04 p.m. |
| PD | Predicate disambiguation | batch_69f673c4abec8190bc2379e66f4af0a9 |
completed | May 2, 2026, 9:59 p.m. |
Created at: April 28, 2026, 4:07 a.m.