Triple
T6790
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Works Progress Administration |
E135
|
entity |
| Predicate | employedApproximately |
P803
|
FINISHED |
| Object | 8.5 million people |
—
|
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: 8.5 million people | Statement: [Works Progress Administration, employedApproximately, 8.5 million people]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: employedApproximately Context triple: [Works Progress Administration, employedApproximately, 8.5 million people]
-
A.
employer
Indicates a relationship where one entity hires, pays, and oversees the work of another entity.
-
B.
worksWith
Indicates that two entities collaborate or perform tasks together in a shared work-related context.
-
C.
staffIncluded
Indicates that staff members are included or provided as part of the associated entity, service, or arrangement.
-
D.
commissionedBy
Indicates that one entity has been formally requested, authorized, or hired by another entity to create, perform, or carry out something.
-
E.
isAbout
Indicates that one entity has as its subject, focus, or primary concern the content, topic, or theme represented by another entity.
- 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_69a23bb612708190b09f25385e4b63d1 |
completed | Feb. 28, 2026, 12:49 a.m. |
| NER | Named-entity recognition | batch_69a241a55ac081909e95b71c97db8140 |
completed | Feb. 28, 2026, 1:15 a.m. |
| PD | Predicate disambiguation | batch_69a23fe1cf38819080ea56c40bf2632e |
completed | Feb. 28, 2026, 1:07 a.m. |
| PDg | Predicate description generation | batch_69a241a4a0f481908de66b64c6262fcd |
completed | Feb. 28, 2026, 1:15 a.m. |
Created at: Feb. 28, 2026, 12:54 a.m.