Triple
T36788199
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | "Where Is Love?" |
E908979
|
entity |
| Predicate | singingVoiceIn1968Film |
P158643
|
FINISHED |
| Object | Kathe Green |
—
|
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: Kathe Green | Statement: ["Where Is Love?", singingVoiceIn1968Film, Kathe Green]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: singingVoiceIn1968Film Context triple: ["Where Is Love?", singingVoiceIn1968Film, Kathe Green]
-
A.
singsVoiceBy
Indicates that a singing performance is rendered using a particular voice or vocal part.
-
B.
hasSingingVoiceType
Indicates the specific category or classification of a person's singing voice (such as soprano, tenor, etc.) in relation to that person.
-
C.
sangSoundtrackFor
Indicates that one entity performed or recorded the soundtrack music for a work associated with another entity.
-
D.
sungInFilmBy
chosen
Indicates that a particular song was vocally performed in a film by a specific person or group.
-
E.
vocalInterpretationOf
Indicates that one entity is a vocal performance or rendition that expresses, realizes, or interprets the content 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_69f76e7a937c81909ed7359641e670f6 |
completed | May 3, 2026, 3:49 p.m. |
| NER | Named-entity recognition | batch_69f7ca93bd0481909d6eee9e950001a1 |
completed | May 3, 2026, 10:22 p.m. |
| PD | Predicate disambiguation | batch_69f7c89b528c8190bf80b230fc7c7108 |
completed | May 3, 2026, 10:13 p.m. |
Created at: May 3, 2026, 4:12 p.m.