Triple
T21451815
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Sandra Howard |
E529226
|
entity |
| Predicate | spouse |
P13
|
FINISHED |
| Object | Michael Howard |
—
|
NE NERFINISHED |
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: Michael Howard | Statement: [Sandra Howard, spouse, Michael Howard]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Michael Howard Context triple: [Sandra Howard, spouse, Michael Howard]
-
A.
Michael Howard
chosen
Michael Howard is a British Conservative politician who served as Leader of the Conservative Party and Leader of the Opposition in the early 2000s.
-
B.
Sir Michael Howard
Sir Michael Howard was a distinguished British military historian and academic renowned for his influential works on war, strategy, and European history.
-
C.
Andrew Howard
Andrew Howard is a Welsh actor known for his intense character roles in film and television, including a supporting role in the thriller "Limitless."
-
D.
Andrew Howard
Andrew Howard is a computer vision researcher and engineer best known for his work on efficient deep neural network architectures, including leading the development of MobileNetV2.
-
E.
Rupert Heseltine
Rupert Heseltine is a British media executive known for his leadership role at Haymarket Media Group, the publishing company founded by his father, Michael Heseltine.
- F. None of above.
- G. Unsure - the case is ambiguous/there is not enough information to decide.
Provenance (2 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_69e0c457579481909db68053ed99750c |
completed | April 16, 2026, 11:13 a.m. |
| NER | Named-entity recognition | batch_69e9e9d33e648190864b0ef5acf36659 |
completed | April 23, 2026, 9:43 a.m. |
Created at: April 16, 2026, 6:07 p.m.