Triple
T36395480
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Devers, Texas |
E896462
|
entity |
| Predicate | geographicDirectionInTexas |
P44650
|
FINISHED |
| Object | southeastern 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: southeastern Texas | Statement: [Devers, Texas, geographicDirectionInTexas, southeastern Texas]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: geographicDirectionInTexas Context triple: [Devers, Texas, geographicDirectionInTexas, southeastern Texas]
-
A.
directionFromAustin
Indicates the cardinal or relative compass direction in which one entity is located from Austin.
-
B.
directionFromDallas–FortWorthMetroplex
Indicates the cardinal or relative compass direction in which one entity is located from the Dallas–Fort Worth Metroplex.
-
C.
geographicDirectionWithinState
chosen
Indicates that one location lies in a specified cardinal or relative geographic direction within the boundaries of a particular state.
-
D.
directionFromFortWorth
Indicates the compass direction in which one entity is located relative to Fort Worth.
-
E.
directionFromHouston
Indicates the cardinal or relative compass direction of one location as measured from Houston.
- 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_69f76e52e3108190becf70b090ae7bd6 |
completed | May 3, 2026, 3:48 p.m. |
| NER | Named-entity recognition | batch_69fd05ba6b2c81909c62b46237d10365 |
completed | May 7, 2026, 9:35 p.m. |
| PD | Predicate disambiguation | batch_69fd03039e48819082b6e12c5453885a |
completed | May 7, 2026, 9:24 p.m. |
Created at: May 3, 2026, 4:10 p.m.