Triple
T17932598
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Walking on Broken Glass |
E448370
|
entity |
| Predicate | includedInAlbum |
P1925
|
FINISHED |
| Object | Diva |
—
|
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: Diva | Statement: [Walking on Broken Glass, includedInAlbum, Diva]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Diva Context triple: [Walking on Broken Glass, includedInAlbum, Diva]
-
A.
Diva
"Diva" is a swaggering, club-ready R&B/pop track by Beyoncé that celebrates female confidence and star power.
-
B.
Diva
Diva is a 1981 French cult thriller film by Jean-Jacques Beineix, celebrated for its stylish visuals, blending of genres, and influence on the cinéma du look movement.
-
C.
Diva
chosen
Diva is Annie Lennox’s acclaimed 1992 debut solo studio album, noted for its sophisticated pop sound and emotionally powerful vocals.
-
D.
Diva
Diva is a superheroine from the WildStorm comic series "Stormwatch," known for her sonic-based powers and role on the UN-sanctioned superhuman team.
-
E.
Diva Donna
Diva Donna is the onstage persona representing Donna Summer at the height of her fame in the jukebox musical "Summer: The Donna Summer Musical."
- F. None of above.
- G. Unsure - the case is ambiguous/there is not enough information to decide.
Provenance (2 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_69d8b9f79d14819095540856928f0e25 |
completed | April 10, 2026, 8:51 a.m. |
| NER | Named-entity recognition | batch_69e4a55381708190b5dfce6a81bb20d8 |
completed | April 19, 2026, 9:50 a.m. |
Created at: April 10, 2026, 10:20 a.m.