Triple
T10261867
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Ego |
E240617
|
entity |
| Predicate | writer |
P1360
|
FINISHED |
| Object | Elvis Williams |
E835961
|
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: Elvis Williams | Statement: [Ego, writer, Elvis Williams]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Elvis Williams Context triple: [Ego, writer, Elvis Williams]
-
A.
Elvis Williams
chosen
Elvis Williams is a writer known for work associated with the publication or project "Glamorous."
-
B.
Coco Williams
Coco Williams is a daughter of British singer-songwriter Robbie Williams.
-
C.
Mancel Warrick
Mancel Warrick was the father of American soul and R&B singer Dee Dee Warwick and a member of the musical Warwick family.
-
D.
Mike Williams
Mike Williams is a Swedish computer scientist best known as one of the creators of the Erlang programming language.
-
E.
Mike Williams
Mike Williams is the real-life chief electronics technician whose experiences during the 2010 Deepwater Horizon oil rig disaster were dramatized in the film "Deepwater Horizon."
- 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_69d381a7e198819090280d5ab885d59e |
completed | April 6, 2026, 9:49 a.m. |
| NER | Named-entity recognition | batch_69d4d25c8dec8190af9160d9338ffc9c |
completed | April 7, 2026, 9:46 a.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69d6f7f81dd481909022efde8fc46e68 |
completed | April 9, 2026, 12:51 a.m. |
Created at: April 6, 2026, 11:32 a.m.