Triple
T29029905
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | SAS Institute |
E737699
|
entity |
| Predicate | hasEmployeeBenefit |
P2188
|
FINISHED |
| Object | on-site daycare at headquarters |
—
|
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: on-site daycare at headquarters | Statement: [SAS Institute, hasEmployeeBenefit, on-site daycare at headquarters]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: hasEmployeeBenefit Context triple: [SAS Institute, hasEmployeeBenefit, on-site daycare at headquarters]
-
A.
hasBenefit
chosen
Indicates that one entity provides an advantage, improvement, or positive outcome to another entity.
-
B.
hasBenefitType
Indicates that an entity is associated with a specific category or type of benefit it provides or receives.
-
C.
hasBenefitDesign
Indicates that an entity possesses or is associated with a particular benefit-related design or configuration.
-
D.
benefitAdministered
Indicates that a benefit (such as aid, service, or entitlement) has been formally provided or delivered to an eligible recipient by an administering party.
-
E.
isIndividualBenefit
Indicates that something provides a benefit or advantage to a single individual rather than to a group or collective.
- 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_69f077ef00fc81909325f084ad37c035 |
completed | April 28, 2026, 9:03 a.m. |
| NER | Named-entity recognition | batch_69f6600d85008190b540a39f7cda88d3 |
completed | May 2, 2026, 8:35 p.m. |
| PD | Predicate disambiguation | batch_69f65c2376a08190be5215171e908e69 |
completed | May 2, 2026, 8:18 p.m. |
Created at: April 28, 2026, 9:54 a.m.