Triple
T10079893
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Killeen, Texas |
E213872
|
entity |
| Predicate | adjacentTo |
P224
|
FINISHED |
| Object | Fort Hood |
E29240
|
NE 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: Fort Hood | Statement: [Killeen, Texas, adjacentTo, Fort Hood]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Fort Hood Context triple: [Killeen, Texas, adjacentTo, Fort Hood]
-
A.
Fort Bliss
Fort Bliss is a major United States Army installation in West Texas and New Mexico, known for air defense artillery training and extensive desert training grounds.
-
B.
Fort Sam Houston
Fort Sam Houston is a major U.S. Army installation in San Antonio, Texas, known for its historic role in military training, command, and medical operations.
-
C.
Fort Cavazos
chosen
Fort Cavazos is a major U.S. Army installation in Texas that serves as a key training and operational base for armored and mechanized forces.
-
D.
Fort Wolters
Fort Wolters is a former U.S. Army training base near Mineral Wells, Texas, best known as a major helicopter training center during the Vietnam War era.
-
E.
Fort Dix
Fort Dix is a major U.S. Army installation in New Jersey that has long served as a key training and mobilization center for American soldiers.
- F. None of above.
- G. Unsure - the case is ambiguous/there is not enough information to decide.
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_69ca839bf730819086900c323c9b8c95 |
completed | March 30, 2026, 2:07 p.m. |
| NER | Named-entity recognition | batch_69cdd031ce748190bb71189afd331979 |
completed | April 2, 2026, 2:10 a.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69d2cbcc82988190903efb78d0a4ce81 |
completed | April 5, 2026, 8:53 p.m. |
Created at: March 30, 2026, 9 p.m.