Triple
T19758646
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Shirlie Holliman |
E474568
|
entity |
| Predicate | partner |
P1136
|
FINISHED |
| Object | Martin Kemp |
E104146
|
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: Martin Kemp | Statement: [Shirlie Holliman, partner, Martin Kemp]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Martin Kemp Context triple: [Shirlie Holliman, partner, Martin Kemp]
-
A.
Martin Kemp
chosen
Martin Kemp is an English musician and actor best known as the bassist of the new wave band Spandau Ballet and for his role as Steve Owen in the BBC soap opera EastEnders.
-
B.
Martin Kemp
Martin Kemp is a British art historian and Leonardo da Vinci specialist renowned for his scholarship on Renaissance art and the relationship between art and science.
-
C.
Michael Baxandall
Michael Baxandall was a highly influential British art historian best known for his groundbreaking studies of Renaissance art and the social conditions shaping artistic style.
-
D.
Nicholas Tomalin
Nicholas Tomalin was a British journalist and war correspondent known for his vivid reporting and for being killed while covering the Yom Kippur War in 1973.
-
E.
John Blick
John Blick is a cinematographer best known for his work on the supernatural horror-comedy film "The Frighteners."
- 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_69d8e51940a0819087bd2996f98da668 |
completed | April 10, 2026, 11:55 a.m. |
| NER | Named-entity recognition | batch_69e6531d711c8190996fcf967c39c523 |
completed | April 20, 2026, 4:23 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_6a07c4f1000481909efe0d10869596ed |
completed | May 16, 2026, 1:14 a.m. |
Created at: April 10, 2026, 1:48 p.m.