Triple
T16948911
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Korean War U.S. Army infantry veterans |
E411134
|
entity |
| Predicate | servedInUnitType |
P56843
|
FINISHED |
| Object | infantry division |
—
|
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: infantry division | Statement: [Korean War U.S. Army infantry veterans, servedInUnitType, infantry division]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: servedInUnitType Context triple: [Korean War U.S. Army infantry veterans, servedInUnitType, infantry division]
-
A.
militaryUnitTypeServed
chosen
Indicates that an entity served in, or was a member of, a specific type of military unit.
-
B.
servedInRole
Indicates that one entity performed duties or held a position within a specified role or office in relation to another entity.
-
C.
militaryUnitOf
Indicates that one entity is a military unit that belongs to, is part of, or is under the command or organizational structure of another entity.
-
D.
involvedUnit
Indicates that a particular unit (such as a group, organization, or division) participates in, is associated with, or plays a role in the referenced event or activity.
-
E.
listedUnit
Indicates that an entity is specified or recorded as a particular unit in a list or catalog.
- 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_69d886c886688190967be07322597ac9 |
completed | April 10, 2026, 5:12 a.m. |
| NER | Named-entity recognition | batch_69e3cfb4b1b08190b608d36a209ed6bd |
completed | April 18, 2026, 6:38 p.m. |
| PD | Predicate disambiguation | batch_69e32b9aa8748190b248890aca86753d |
completed | April 18, 2026, 6:58 a.m. |
Created at: April 10, 2026, 5:31 a.m.