Triple
T10002633
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Public Law 99-272 |
E197363
|
entity |
| Predicate | qualifyingEventsInclude |
P58905
|
FINISHED |
| Object | termination of employment |
—
|
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: termination of employment | Statement: [Public Law 99-272, qualifyingEventsInclude, termination of employment]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: qualifyingEventsInclude Context triple: [Public Law 99-272, qualifyingEventsInclude, termination of employment]
-
A.
qualifyingEvent
Indicates that an event meets specific conditions or criteria that make an entity eligible for a particular status, action, or outcome.
-
B.
includesEvents
chosen
Indicates that one entity contains or encompasses one or more events as part of its scope or composition.
-
C.
eligibleCompetition
Indicates that an entity meets the required conditions to participate in a particular competition.
-
D.
participationIncludes
Indicates that a broader participation instance encompasses or contains a more specific participation instance as part of it.
-
E.
multiEventsIncluded
Indicates that multiple distinct events are collectively contained within, or form part of, a larger event set or grouping.
- 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_69ca82f3b61c81908ecc2c1c96dbc2e4 |
completed | March 30, 2026, 2:04 p.m. |
| NER | Named-entity recognition | batch_69cdcc9078788190a4e75dd7ff830c63 |
completed | April 2, 2026, 1:55 a.m. |
| PD | Predicate disambiguation | batch_69cd1da2cf9081908a6c0eb5247d0bc2 |
completed | April 1, 2026, 1:29 p.m. |
Created at: March 30, 2026, 8:51 p.m.