Triple
T36749692
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Haltemprice and Howden |
E907870
|
entity |
| Predicate | representedIn2019 |
P200484
|
FINISHED |
| Object | David Davis |
—
|
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: David Davis | Statement: [Haltemprice and Howden, representedIn2019, David Davis]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: representedIn2019 Context triple: [Haltemprice and Howden, representedIn2019, David Davis]
-
A.
representedIn2017
Indicates that something served as a representation or was depicted/expressed in the year 2017.
-
B.
representedIn2015
Indicates that something was depicted, portrayed, or otherwise shown within a context specifically in the year 2015.
-
C.
representedIn2010sBy
Indicates that one entity served as the representative, depiction, or embodiment of another entity specifically during the 2010s decade.
-
D.
representedInOffice
Indicates that an entity serves as an official representative of another entity within a specific office or governmental body.
-
E.
includedRepresentativesFrom
Indicates that one entity’s composition or delegation contained representatives originating from another specified entity.
- F. None of above. chosen
Provenance (4 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_69f76e76d10881909ec1679bc043108c |
completed | May 3, 2026, 3:49 p.m. |
| NER | Named-entity recognition | batch_69ff8cecbf048190860b9f72b8753f5c |
completed | May 9, 2026, 7:37 p.m. |
| PD | Predicate disambiguation | batch_69ff8c4c39dc8190b5bf35adc1bae7c6 |
completed | May 9, 2026, 7:34 p.m. |
| PDg | Predicate description generation | batch_69ff8cec1e4c8190b2d66b3e0f913bfd |
completed | May 9, 2026, 7:37 p.m. |
Created at: May 3, 2026, 4:12 p.m.