Triple
T10536839
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Mabel Williams |
E248587
|
entity |
| Predicate | sibling |
P363
|
FINISHED |
| Object | Thomas Lyle Williams |
E176044
|
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 Lyle Williams | Statement: [Mabel Williams, sibling, Thomas Lyle Williams]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Thomas Lyle Williams Context triple: [Mabel Williams, sibling, Thomas Lyle Williams]
-
A.
Thomas Lyle Williams
chosen
Thomas Lyle Williams was an American entrepreneur best known for creating the Maybelline cosmetics brand, which became one of the world’s leading makeup companies.
-
B.
William Eric Williams
William Eric Williams is the son of American modernist poet and physician William Carlos Williams.
-
C.
Robert Wynn Williams
Robert Wynn Williams was a British politician who served as a Member of Parliament for the Caernarvon Boroughs constituency.
-
D.
Mahlon Todd Williams
Mahlon Todd Williams is a cinematographer best known for his work on the animated feature film "PAW Patrol: The Movie."
-
E.
Robert Lynn Williamson
Robert Lynn Williamson was an American tobacco executive best known as a founder of the major cigarette manufacturer Brown & Williamson.
- 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_69d381c5c7448190bec34bee7ec72bac |
completed | April 6, 2026, 9:49 a.m. |
| NER | Named-entity recognition | batch_69d50a554fb4819081e9618bab051dc6 |
completed | April 7, 2026, 1:44 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69d90e507b408190ae3538d02536ef4c |
completed | April 10, 2026, 2:50 p.m. |
Created at: April 6, 2026, 12:31 p.m.