Triple
T4748544
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | United States Army Criminal Investigation Division |
E105420
|
entity |
| Predicate | usesRankTitle |
P10405
|
FINISHED |
| Object | special agent |
—
|
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: special agent | Statement: [United States Army Criminal Investigation Division, usesRankTitle, special agent]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: usesRankTitle Context triple: [United States Army Criminal Investigation Division, usesRankTitle, special agent]
-
A.
usesRank
Indicates that one entity applies or relies on a ranking or ordered level system associated with another entity.
-
B.
usesRankStructure
Indicates that an entity organizes its members or components according to a defined hierarchical rank structure.
-
C.
usesTitle
chosen
Indicates that one entity refers to or addresses another entity using a specific title or formal designation.
-
D.
isRank
Indicates that one entity serves as the rank, level, or hierarchical position associated with another entity.
-
E.
namedForRank
Indicates that something is named after a specific rank or title held by an entity.
- 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_69bd43f07fa48190954317d01600994a |
completed | March 20, 2026, 12:56 p.m. |
| NER | Named-entity recognition | batch_69bd64c6f5ac81908a62f9c17e77ac86 |
completed | March 20, 2026, 3:16 p.m. |
| PD | Predicate disambiguation | batch_69bd6223defc8190823665a6592c1154 |
completed | March 20, 2026, 3:05 p.m. |
Created at: March 20, 2026, 1:20 p.m.