Triple
T9946819
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | FBI contractors |
E195223
|
entity |
| Predicate | employedThrough |
P91296
|
FINISHED |
| Object | private companies |
—
|
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: private companies | Statement: [FBI contractors, employedThrough, private companies]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: employedThrough Context triple: [FBI contractors, employedThrough, private companies]
-
A.
employedTo
Indicates that one entity is hired or engaged to perform work, services, or duties for another entity.
-
B.
employedSystem
Indicates that a system is used or operated in the context of an employment or work-related arrangement.
-
C.
employedApproximately
Indicates that one entity employs another in a manner where the number, duration, or extent of employment is approximate rather than exact.
-
D.
employedPeople
Indicates that there exists a relationship where people are currently working in jobs or positions, typically under an employer.
-
E.
employedRole
Indicates that an entity holds or performs a specific role or position within an employment or work context.
- 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_69ca82e96a108190932bd1fc4acd73a0 |
completed | March 30, 2026, 2:04 p.m. |
| NER | Named-entity recognition | batch_69cdb657b35c81909448e93999f6e77c |
completed | April 2, 2026, 12:20 a.m. |
| PD | Predicate disambiguation | batch_69cd1d97c44081908730071269f07712 |
completed | April 1, 2026, 1:28 p.m. |
| PDg | Predicate description generation | batch_69cd358386f48190833c862b5b8c04b2 |
completed | April 1, 2026, 3:10 p.m. |
Created at: March 30, 2026, 8:45 p.m.