Triple
T15950453
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Feels Good |
E386801
|
entity |
| Predicate | producer |
P490
|
FINISHED |
| Object | Thomas McElroy |
E1183038
|
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: Thomas McElroy | Statement: [Feels Good, producer, Thomas McElroy]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Thomas McElroy Context triple: [Feels Good, producer, Thomas McElroy]
-
A.
Thomas McElroy
chosen
Thomas McElroy is an American songwriter and record producer best known as a member of the R&B group Club Nouveau and for his influential work in late-1980s and 1990s contemporary R&B.
-
B.
Michael McElroy
Michael McElroy is an American actor and Tony-nominated Broadway performer known for his work in musical theatre and film.
-
C.
Roger O'Connor
Roger O'Connor was an Irish nationalist and writer known for his radical political views in the late 18th and early 19th centuries.
-
D.
Bill Heelan
Bill Heelan is a developer best known for creating the software project Archie.
-
E.
Hugh McDermott
Hugh McDermott was a Scottish actor known for his supporting roles in British films of the 1930s and 1940s.
- 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_69d86da882448190a82ea962fe343b79 |
completed | April 10, 2026, 3:25 a.m. |
| NER | Named-entity recognition | batch_69e156d4c5008190a56ebf8c28f712dc |
completed | April 16, 2026, 9:38 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_6a030c468b508190a1d683ff354c235c |
completed | May 12, 2026, 11:17 a.m. |
Created at: April 10, 2026, 4:53 a.m.