Triple
T4984
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | J. Erik Jonsson |
E97
|
entity |
| Predicate | officeStartTime |
P288
|
FINISHED |
| Object | 1964 (mayor of Dallas) |
—
|
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: 1964 (mayor of Dallas) | Statement: [J. Erik Jonsson, officeStartTime, 1964 (mayor of Dallas)]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: officeStartTime Context triple: [J. Erik Jonsson, officeStartTime, 1964 (mayor of Dallas)]
-
A.
startDate
chosen
Indicates the point in time when an event, state, or relationship begins.
-
B.
orderInOffice
Indicates that one entity holds a specific sequential position or rank within a defined term or period of holding an office or official role.
-
C.
ranForOffice
Indicates that an entity was a candidate seeking election to a public or organizational office.
-
D.
leftOffice
Indicates that an entity ceased holding or performing the duties of a particular office or position.
-
E.
locatedInTimeZone
Indicates that an entity exists or an event occurs within the temporal bounds defined by a specific time zone.
- 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_69a238d6b47881909e68288aed2fd858 |
completed | Feb. 28, 2026, 12:37 a.m. |
| NER | Named-entity recognition | batch_69a23c24b3d08190a714126292fd5479 |
completed | Feb. 28, 2026, 12:51 a.m. |
| PD | Predicate disambiguation | batch_69a23998af288190855f0456740cbd51 |
completed | Feb. 28, 2026, 12:40 a.m. |
Created at: Feb. 28, 2026, 12:40 a.m.