Triple
T37328009
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Ken Clarke |
E926662
|
entity |
| Predicate | precededInOfficeAsChancellor |
P58529
|
FINISHED |
| Object | Norman Lamont |
—
|
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: Norman Lamont | Statement: [Ken Clarke, precededInOfficeAsChancellor, Norman Lamont]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: precededInOfficeAsChancellor Context triple: [Ken Clarke, precededInOfficeAsChancellor, Norman Lamont]
-
A.
precededInOfficeAsChancellorBy
chosen
Indicates that one individual assumed the role of Chancellor after another specific individual, who held the office immediately before them.
-
B.
lastChancellor
Indicates that one entity served as the most recent chancellor of another entity (such as a country, institution, or organization).
-
C.
servedAsHeadOfTheChancelleryFrom
Indicates that a person held the position of head of the chancellery starting from a specified date or time period.
-
D.
formerChancellor
Indicates that one entity previously held the position or role of chancellor of the other entity, but no longer does.
-
E.
hasChancellor
Indicates that an entity holds the position or role of chancellor for another entity.
- F. None of above.
Provenance (3 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_69f76eb386d88190a8d511aa11540dfc |
completed | May 3, 2026, 3:50 p.m. |
| NER | Named-entity recognition | batch_69fdee770af48190aca2670db50f8b49 |
completed | May 8, 2026, 2:08 p.m. |
| PD | Predicate disambiguation | batch_69fdecec98a08190a357d816dc2a6dbe |
completed | May 8, 2026, 2:02 p.m. |
Created at: May 3, 2026, 4:16 p.m.