Triple
T28297897
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Holborn and St Pancras (UK Parliament constituency) |
E713618
|
entity |
| Predicate | FrankDobsonServedAsMPUntil |
P164673
|
FINISHED |
| Object | 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: 2015 | Statement: [Holborn and St Pancras (UK Parliament constituency), FrankDobsonServedAsMPUntil, 2015]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: FrankDobsonServedAsMPUntil Context triple: [Holborn and St Pancras (UK Parliament constituency), FrankDobsonServedAsMPUntil, 2015]
-
A.
Tony Benn_termEnd
Indicates the date or point in time when Tony Benn’s term in a particular office or position ended.
-
B.
termEndAsMPForDover
Indicates that a person’s term of service as a Member of Parliament representing the constituency of Dover has ended.
-
C.
TonyBlairHeldSeatUntil
Indicates that Tony Blair occupied a particular political seat or office up to and including a specified end date.
-
D.
termEndAsLeaderOfConservativeParty
Indicates that an individual’s tenure as leader of the Conservative Party has concluded.
-
E.
representedInParliamentSince
Indicates that an entity has held representation in a parliament continuously from a specified starting time.
- 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_69efb524ab688190a1ce7ee7c9520932 |
completed | April 27, 2026, 7:12 p.m. |
| NER | Named-entity recognition | batch_69f64ee0c2788190a94a04ad1902fd5e |
completed | May 2, 2026, 7:22 p.m. |
| PD | Predicate disambiguation | batch_69f64caede108190a35cc7cbfead866f |
completed | May 2, 2026, 7:12 p.m. |
| PDg | Predicate description generation | batch_69f64e36c57c8190af09470a8d35512b |
completed | May 2, 2026, 7:19 p.m. |
Created at: April 27, 2026, 11:33 p.m.