Triple
T26154293
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Bermondsey and Old Southwark (UK Parliament constituency) |
E659913
|
entity |
| Predicate | representedByFrom |
P177097
|
FINISHED |
| Object | Neil Coyle from 2015 |
—
|
LITERAL 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: Neil Coyle from 2015 | Statement: [Bermondsey and Old Southwark (UK Parliament constituency), representedByFrom, Neil Coyle from 2015]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: representedByFrom Context triple: [Bermondsey and Old Southwark (UK Parliament constituency), representedByFrom, Neil Coyle from 2015]
-
A.
representedFrom
Indicates that one entity serves as a representation or depiction of another entity.
-
B.
representedByAttribute
Indicates that one entity serves as an attribute-based representation or characterization of another entity.
-
C.
areRepresentedBy
Indicates that one entity serves as a representation, proxy, or stand-in for another entity.
-
D.
representedByEnd
Indicates that something is represented or characterized by its endpoint or final part.
-
E.
hasRepresentationFrom
Indicates that something serves as a representation, depiction, or encoding that originates from or is derived from another 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_69ee5bc5a9908190899d39ce95c6d215 |
completed | April 26, 2026, 6:39 p.m. |
| NER | Named-entity recognition | batch_69f6f85bfba48190aba95b40642a8ca7 |
completed | May 3, 2026, 7:25 a.m. |
| PD | Predicate disambiguation | batch_69f6f65fd1d08190b88e5e68ba268500 |
completed | May 3, 2026, 7:16 a.m. |
| PDg | Predicate description generation | batch_69f6f854486c81909396d944a55e03ab |
completed | May 3, 2026, 7:25 a.m. |
Created at: April 26, 2026, 8:27 p.m.