Triple
T33251168
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Edmund J. Davis |
E851245
|
entity |
| Predicate | priorOffice |
P18982
|
FINISHED |
| Object | district judge in Texas |
—
|
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: district judge in Texas | Statement: [Edmund J. Davis, priorOffice, district judge in Texas]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: priorOffice Context triple: [Edmund J. Davis, priorOffice, district judge in Texas]
-
A.
previousOffice
Indicates that one office or position was held immediately before another in a sequence of offices.
-
B.
priorService
Indicates that one entity has previously provided service or served in a role, position, or capacity before the current context or event.
-
C.
priorCourt
Indicates that one court or legal proceeding occurred before another in time or procedural sequence.
-
D.
officePreviouslyHeldBy
chosen
Indicates that a particular office or position was formerly occupied by a specified person or entity.
-
E.
laterOffice
Indicates that one office or term of office occurs chronologically after another office or term.
- 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_69f34963135c819084e7f1d483421f00 |
completed | April 30, 2026, 12:21 p.m. |
| NER | Named-entity recognition | batch_69f6db2b1be88190bef6c2ca36eae580 |
completed | May 3, 2026, 5:20 a.m. |
| PD | Predicate disambiguation | batch_69f6d82fef788190b9ad19a36c0312dc |
completed | May 3, 2026, 5:08 a.m. |
Created at: May 1, 2026, 1:31 a.m.