Triple
T15457185
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Glyn |
E371799
|
entity |
| Predicate | hasNotableBearer |
P458
|
FINISHED |
| Object | Glyn Houston |
E203148
|
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: Glyn Houston | Statement: [Glyn, hasNotableBearer, Glyn Houston]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Glyn Houston Context triple: [Glyn, hasNotableBearer, Glyn Houston]
-
A.
Glyn Houston
chosen
Glyn Houston was a Welsh character actor known for his extensive work in British film and television from the 1950s onward.
-
B.
Glyn Williams
Glyn Williams is a British sculptor known for creating prominent public monuments, including the statue of David Lloyd George in Parliament Square, London.
-
C.
Glyn Davies
Glyn Davies is a Welsh economist and academic best known for his influential work on the history of money and banking.
-
D.
Glyn Simon
Glyn Simon was a Welsh Anglican bishop who served as Archbishop of Wales in the mid-20th century.
-
E.
Huw Bennett
Huw Bennett is a Welsh former international rugby union player who played as a hooker, most notably for the Ospreys and the Wales national team.
- 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_69d85cc8bd308190886949510b42e764 |
completed | April 10, 2026, 2:13 a.m. |
| NER | Named-entity recognition | batch_69e03f146a2c8190882741af3ec15268 |
completed | April 16, 2026, 1:44 a.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69ff365504488190a6f43d82d008c855 |
completed | May 9, 2026, 1:27 p.m. |
Created at: April 10, 2026, 3:31 a.m.