Triple
T17661053
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Nuclear Technologies and Materials |
E440251
|
entity |
| Predicate | servesCustomerSector |
P2193
|
FINISHED |
| Object | government agencies |
—
|
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: government agencies | Statement: [Nuclear Technologies and Materials, servesCustomerSector, government agencies]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: servesCustomerSector Context triple: [Nuclear Technologies and Materials, servesCustomerSector, government agencies]
-
A.
sectorServed
chosen
Indicates the industry or economic sector that an entity primarily serves or targets with its activities, products, or services.
-
B.
ownerSector
Indicates the sector or industry category to which the owner of an entity belongs.
-
C.
sectorOfOperation
Indicates the industry, domain, or field within which an entity conducts its primary activities or operations.
-
D.
sectoralCoverage
Indicates the specific sectors, industries, or domains to which something (such as a policy, agreement, or dataset) applies or extends.
-
E.
hasCustomerIndustry
Indicates that a customer is associated with or operates within a particular industry or sector.
- 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_69d8b9e87e18819087104a44dc4dc5b1 |
completed | April 10, 2026, 8:50 a.m. |
| NER | Named-entity recognition | batch_69e46ea67f8081909da164ca21a98675 |
completed | April 19, 2026, 5:56 a.m. |
| PD | Predicate disambiguation | batch_69e3cde007d8819090dd92eea9f022cc |
completed | April 18, 2026, 6:30 p.m. |
Created at: April 10, 2026, 9:43 a.m.