Triple
T4009669
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Virginia Peninsula |
E90611
|
entity |
| Predicate | contains |
P35
|
FINISHED |
| Object | Fort Eustis |
E26629
|
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 Eustis | Statement: [Virginia Peninsula, contains, Fort Eustis]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Fort Eustis Context triple: [Virginia Peninsula, contains, Fort Eustis]
-
A.
Fort Eustis, Virginia
chosen
Fort Eustis, Virginia is a major U.S. Army installation in Newport News known for its role in training, logistics, and aviation support.
-
B.
Fort McClellan
Fort McClellan is a former U.S. Army installation near Anniston, Alabama, historically used for infantry, military police, and chemical corps training.
-
C.
Fort Gregg-Adams
Fort Gregg-Adams is a major U.S. Army installation in Virginia that serves as the primary training and doctrine center for logistics, sustainment, and related support specialties.
-
D.
Fort Richardson
Fort Richardson was a former United States Army post near Anchorage, Alaska, that later became part of Joint Base Elmendorf–Richardson.
-
E.
Fort Stewart
Fort Stewart is a major U.S. Army installation in southeastern Georgia that serves as a key training and deployment base for armored and mechanized units.
- 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_69aed95e44088190aff7d90a151b1b20 |
completed | March 9, 2026, 2:29 p.m. |
| NER | Named-entity recognition | batch_69aefa8579288190940487ad07e38de0 |
completed | March 9, 2026, 4:51 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69b54c6df2e88190b6fd58bd8102d62a |
completed | March 14, 2026, 11:54 a.m. |
Created at: March 9, 2026, 3:34 p.m.