Triple
T28117900
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | James Barbour |
E710689
|
entity |
| Predicate | officeHeldForTerm |
P17403
|
FINISHED |
| Object | Governor of Virginia |
—
|
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: Governor of Virginia | Statement: [James Barbour, officeHeldForTerm, Governor of Virginia]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: officeHeldForTerm Context triple: [James Barbour, officeHeldForTerm, Governor of Virginia]
-
A.
appointedTerm
Indicates that an entity has been officially assigned to hold a position or role for a specified term or duration.
-
B.
termInOffice
chosen
Indicates the period during which an individual officially holds a particular office or position.
-
C.
officeHeldOf
Indicates that a specific office or position is (or was) held by a particular person or entity.
-
D.
termOfOfficeResult
Indicates the outcome or status associated with a specific term of office, such as whether it was completed, successful, or ended in a particular way.
-
E.
officeHeldDuring
Indicates that a person occupied a specific official position during a particular time period.
- 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_69ef9b72f63081909dfbc2c1ddae86c6 |
completed | April 27, 2026, 5:22 p.m. |
| NER | Named-entity recognition | batch_69fd5bf69acc819092a01e4259785dc3 |
completed | May 8, 2026, 3:43 a.m. |
| PD | Predicate disambiguation | batch_69fd59b3f4ac8190a7f9dd3142da6e09 |
completed | May 8, 2026, 3:34 a.m. |
Created at: April 27, 2026, 9:15 p.m.