Triple
T24534135
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Stars in Their Eyes |
E606897
|
entity |
| Predicate | hasCelebrityVersion |
P156633
|
FINISHED |
| Object | Celebrity Stars in Their Eyes |
—
|
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: Celebrity Stars in Their Eyes | Statement: [Stars in Their Eyes, hasCelebrityVersion, Celebrity Stars in Their Eyes]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: hasCelebrityVersion Context triple: [Stars in Their Eyes, hasCelebrityVersion, Celebrity Stars in Their Eyes]
-
A.
hasKaraokeVersion
Indicates that an entity has a corresponding karaoke (instrumental or sing-along) version of itself.
-
B.
hasCoverVersionPerformer
Indicates that an entity is the performer of a cover version of another entity’s original work.
-
C.
hasCoverVersions
Indicates that a musical work has one or more recorded versions performed or produced by artists other than the original creator.
-
D.
hasAcousticVersionBy
Indicates that one entity is an acoustic version of another, created or performed by a specified agent.
-
E.
hasFamousVersionTempo
Indicates that one entity is a tempo that characterizes a well-known or widely recognized version of another entity (such as a musical work or performance).
- F. None of above. chosen
Provenance (4 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_69e2c4c90c848190b23c4303620dcaaf |
completed | April 17, 2026, 11:39 p.m. |
| NER | Named-entity recognition | batch_69f2be044d4c819094e14eda28d371a7 |
completed | April 30, 2026, 2:27 a.m. |
| PD | Predicate disambiguation | batch_69f2a6b0ca8081908d931aec560eae56 |
completed | April 30, 2026, 12:47 a.m. |
| PDg | Predicate description generation | batch_69f2b8b8bc5881908df49c0b07110246 |
completed | April 30, 2026, 2:04 a.m. |
Created at: April 18, 2026, 2:25 a.m.