Triple
T1915
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | National Science Foundation |
E35
|
entity |
| Predicate | employs |
P7
|
FINISHED |
| Object | civilian federal employees |
—
|
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: civilian federal employees | Statement: [National Science Foundation, employs, civilian federal employees]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: employs Context triple: [National Science Foundation, employs, civilian federal employees]
-
A.
employer
chosen
Indicates a relationship where one entity hires, pays, and oversees the work of another entity.
-
B.
fieldOfWork
Indicates the professional or academic domain in which an entity is primarily engaged or specializes.
-
C.
usedFor
Indicates that one entity serves a purpose, function, or role in accomplishing, enabling, or supporting another entity or activity.
-
D.
elects
Indicates that one entity selects or chooses another entity for a position, role, or office, typically through a formal voting process.
-
E.
requires
Indicates that one entity must exist, occur, or be satisfied before another entity can exist, occur, or be carried out.
- 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_69a22cde80848190b62c5f556b4d62ba |
completed | Feb. 27, 2026, 11:46 p.m. |
| NER | Named-entity recognition | batch_69a23344daf8819083118bbac5f46568 |
completed | Feb. 28, 2026, 12:13 a.m. |
| PD | Predicate disambiguation | batch_69a232e52e7c81909c072703e28e8c61 |
completed | Feb. 28, 2026, 12:12 a.m. |
Created at: Feb. 27, 2026, 11:48 p.m.