Triple
T9907886
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Modus Vivendi |
E185060
|
entity |
| Predicate | hasPart |
P35
|
FINISHED |
| Object | Glitter |
E146350
|
NE 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: Glitter | Statement: [Modus Vivendi, hasPart, Glitter]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Glitter Context triple: [Modus Vivendi, hasPart, Glitter]
-
A.
Glitter
Glitter is a 2001 musical romantic drama film starring Mariah Carey as an aspiring singer navigating love and the music industry in 1980s New York City.
-
B.
Glitter
"Glitter" is an introspective, genre-blending EP by 070 Shake that helped establish her as a distinctive voice in contemporary hip-hop and alternative R&B.
-
C.
Glitter (album)
chosen
Glitter is the 2001 soundtrack album by Mariah Carey, blending pop, R&B, and disco influences and released alongside her film of the same name.
-
D.
Glitz
Glitz is a crime novel by Elmore Leonard that follows a tough Miami cop entangled with a vengeful ex-con and the seedy underworld of Atlantic City.
-
E.
Sparkle
Sparkle is a Georgia-Pacific paper towel brand known for its affordable, everyday household cleaning products.
- F. None of above.
- G. Unsure - the case is ambiguous/there is not enough information to decide.
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_69ca8296165881908ca4750701af1f29 |
completed | March 30, 2026, 2:03 p.m. |
| NER | Named-entity recognition | batch_69cdb50ec61481908f42bd2aa55d9a6e |
completed | April 2, 2026, 12:15 a.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69d23d22c56081909c3e4b8ca0e81fe7 |
completed | April 5, 2026, 10:44 a.m. |
Created at: March 30, 2026, 8:41 p.m.