Triple
T10115008
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Payment of Members Act 1911 |
E218334
|
entity |
| Predicate | precededByPractice |
P92278
|
FINISHED |
| Object | unpaid service of Members of Parliament |
—
|
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: unpaid service of Members of Parliament | Statement: [Payment of Members Act 1911, precededByPractice, unpaid service of Members of Parliament]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: precededByPractice Context triple: [Payment of Members Act 1911, precededByPractice, unpaid service of Members of Parliament]
-
A.
wasPrecededBy
Indicates that one event, state, or entity occurred or existed earlier in time than another.
-
B.
oftenPrecededBy
Indicates that one event, state, or item commonly occurs or appears before another in time or sequence.
-
C.
classPrecededBy
Indicates that one class occurs or is scheduled before another class in a sequence or timetable.
-
D.
hadPractice
Indicates that an entity engaged in or participated in a practice session or rehearsal.
-
E.
followedPracticeOf
Indicates that one entity adopted, adhered to, or modeled its behavior, methods, or customs after the established practices of 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_69ca83da93fc8190b54e44bc2b34857c |
completed | March 30, 2026, 2:08 p.m. |
| NER | Named-entity recognition | batch_69cdd161831c81908bb3c77caa7c3ce1 |
completed | April 2, 2026, 2:16 a.m. |
| PD | Predicate disambiguation | batch_69cd4b9ed7e48190aa132ef8a69b49f9 |
completed | April 1, 2026, 4:45 p.m. |
| PDg | Predicate description generation | batch_69cd4f8f869c8190a82ad040993e0244 |
completed | April 1, 2026, 5:02 p.m. |
Created at: March 30, 2026, 9:04 p.m.