Triple
T831
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Office of Scientific Research and Development |
E15
|
entity |
| Predicate | significantEvent |
P259
|
FINISHED |
| Object | creation by executive order in 1941 |
—
|
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: creation by executive order in 1941 | Statement: [Office of Scientific Research and Development, significantEvent, creation by executive order in 1941]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: significantEvent Context triple: [Office of Scientific Research and Development, significantEvent, creation by executive order in 1941]
-
A.
notableFor
Indicates that an entity is especially recognized or distinguished for a particular quality, achievement, characteristic, or role.
-
B.
activity
Indicates that an entity is engaged in or performing a particular action, behavior, or process.
-
C.
mission
Indicates that an entity is assigned or engaged in a specific task, operation, or purpose-directed undertaking.
-
D.
notableRecipient
Indicates that an entity has received a notable award, honor, or recognition from another entity.
-
E.
influenced
Indicates that one entity has affected, shaped, or altered another entity’s state, behavior, or characteristics.
- F. None of above. chosen
Provenance (4 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_69a22a285828819081a58308fb963df1 |
completed | Feb. 27, 2026, 11:35 p.m. |
| NER | Named-entity recognition | batch_69a23211f05c8190b8deb03a8540d84d |
completed | Feb. 28, 2026, 12:08 a.m. |
| PD | Predicate disambiguation | batch_69a230c2c48481908beb1db3cc9768aa |
completed | Feb. 28, 2026, 12:03 a.m. |
| PDg | Predicate description generation | batch_69a23211181c81909c2db8796d2aded4 |
completed | Feb. 28, 2026, 12:08 a.m. |
Created at: Feb. 27, 2026, 11:36 p.m.