Triple
T1605946
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | COBRA |
E34502
|
entity |
| Predicate | coverageDuration |
P3058
|
FINISHED |
| Object | typically 18 months for job loss or reduction in hours |
—
|
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: typically 18 months for job loss or reduction in hours | Statement: [COBRA, coverageDuration, typically 18 months for job loss or reduction in hours]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: coverageDuration Context triple: [COBRA, coverageDuration, typically 18 months for job loss or reduction in hours]
-
A.
coverageScope
Indicates the extent or range of entities, conditions, or situations that are included under a particular coverage or applicability.
-
B.
timePeriodCoveredTo
chosen
Indicates the span or duration of time that is encompassed, addressed, or relevant to a given subject or entity.
-
C.
evaDuration
Indicates the length of time that an extravehicular activity (EVA) lasts or is scheduled to last.
-
D.
showDuration
Indicates the length of time for which something is shown, displayed, or performed.
-
E.
completionRate
Indicates the proportion of a task, process, or set of items that has been finished relative to its total intended amount.
- 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_69a885fea6a481909fe83ba6441f1774 |
completed | March 4, 2026, 7:20 p.m. |
| NER | Named-entity recognition | batch_69a93fa6926081908bc78d15c0be3185 |
completed | March 5, 2026, 8:32 a.m. |
| PD | Predicate disambiguation | batch_69a907c35f848190a2428c52e81d013e |
completed | March 5, 2026, 4:34 a.m. |
Created at: March 4, 2026, 7:28 p.m.