Triple
T7251854
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | So Gone |
E157620
|
entity |
| Predicate | composer |
P1361
|
FINISHED |
| Object | Nissan Stewart |
E157620
|
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: Nissan Stewart | Statement: [So Gone, composer, Nissan Stewart]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Nissan Stewart Context triple: [So Gone, composer, Nissan Stewart]
-
A.
Nissan Stewart
chosen
Nissan Stewart is a songwriter and music producer best known for co-writing the R&B hit "So Gone" performed by Monica.
-
B.
Charlie Williams
Charlie Williams was a professional basketball player recognized for his standout performance in the American Basketball Association during the late 1960s, particularly in postseason play.
-
C.
Geoff Burton
Geoff Burton is an Australian cinematographer known for his work on numerous feature films and collaborations with prominent directors.
-
D.
Jack Millar
Jack Millar was an author whose work inspired the creation of the film "The Purple Mask."
-
E.
Robin Midgley
Robin Midgley was a British theatre and television director known for his influential stage work and contributions to contemporary drama.
- 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_69c6882d81d4819085f7ff862951ee4f |
completed | March 27, 2026, 1:37 p.m. |
| NER | Named-entity recognition | batch_69c6ea7ae0e48190bd80c91bad1976c6 |
completed | March 27, 2026, 8:37 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69c7d3a7502081909d2a97a60cc445ae |
completed | March 28, 2026, 1:12 p.m. |
Created at: March 27, 2026, 2:56 p.m.