Triple
T32176507
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Chris Pearson |
E821861
|
entity |
| Predicate | positionFirstHolder |
P3904
|
FINISHED |
| Object | Government Leader of Yukon |
—
|
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: Government Leader of Yukon | Statement: [Chris Pearson, positionFirstHolder, Government Leader of Yukon]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: positionFirstHolder Context triple: [Chris Pearson, positionFirstHolder, Government Leader of Yukon]
-
A.
currentFirstHolder
Indicates that the subject is the entity that currently holds or possesses the object before any subsequent transfer or change of holder.
-
B.
positionHolderMust
Indicates that a person occupying a specific position is required or obligated to perform a certain action or fulfill a particular condition.
-
C.
holderPositionStart
Indicates the starting spatial position or location of the holder in relation to another entity or context.
-
D.
currentHolderStart
Indicates the point in time when an entity’s current holder or possessor first began holding it.
-
E.
hasFirstHolder
chosen
Indicates that an entity is associated with the earliest or original holder (e.g., owner, position-bearer, or title-holder) of something.
- 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_69f3490755288190aee11740a34862f9 |
completed | April 30, 2026, 12:20 p.m. |
| NER | Named-entity recognition | batch_69feafa1ba0081909013800b85a9f613 |
completed | May 9, 2026, 3:53 a.m. |
| PD | Predicate disambiguation | batch_69feae58d62c81909d031f3df8992883 |
completed | May 9, 2026, 3:47 a.m. |
Created at: May 1, 2026, 12:34 a.m.