Triple
T27706
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | National Defense Research Committee |
E552
|
entity |
| Predicate | oversawProjectType |
P1366
|
FINISHED |
| Object | classified military research contracts |
—
|
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: classified military research contracts | Statement: [National Defense Research Committee, oversawProjectType, classified military research contracts]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: oversawProjectType Context triple: [National Defense Research Committee, oversawProjectType, classified military research contracts]
-
A.
typeOfWork
chosen
Indicates the kind or category of work associated with or performed by an entity.
-
B.
operationType
Indicates the specific kind of operation or action being performed or recorded in the relationship between entities.
-
C.
envisionedAs
Indicates that one entity is mentally pictured, imagined, or conceived in terms of another entity or role.
-
D.
obligationType
Indicates the specific kind or category of duty, requirement, or commitment that applies within an obligation relationship.
-
E.
responsibleFor
Indicates that one entity has a duty, obligation, or role to manage, oversee, or be accountable for another entity or outcome.
- 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_69a243b4ac2c8190b93c303df797b7b2 |
completed | Feb. 28, 2026, 1:24 a.m. |
| NER | Named-entity recognition | batch_69a247798a348190bb943d38300ae3ef |
completed | Feb. 28, 2026, 1:40 a.m. |
| PD | Predicate disambiguation | batch_69a24658749881909117b007ec3d8633 |
completed | Feb. 28, 2026, 1:35 a.m. |
Created at: Feb. 28, 2026, 1:34 a.m.