Triple
T35313520
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | ULTRA |
E1019840
|
entity |
| Predicate | requiredCoverHandling |
P200670
|
FINISHED |
| Object | Special Liaison Units |
—
|
NE NERFINISHED |
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: Special Liaison Units | Statement: [ULTRA, requiredCoverHandling, Special Liaison Units]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: requiredCoverHandling Context triple: [ULTRA, requiredCoverHandling, Special Liaison Units]
-
A.
mayCover
Indicates that one entity is permitted or able to extend over, include, or provide coverage for another entity, either partially or fully.
-
B.
providedCoverage
Indicates that one entity supplies or guarantees insurance or protective coverage to another entity or subject.
-
C.
isCoverFor
Indicates that one entity serves as a protective or concealing layer, substitute, or front for another entity or activity.
-
D.
typicallyCovers
Indicates that one entity is the kind of thing that usually or normally includes, addresses, or encompasses another entity.
-
E.
mannerOfCoverage
Indicates the way or style in which something is covered, reported, or presented.
- 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_69f76de9d45c81908a2ed0956b448b65 |
completed | May 3, 2026, 3:46 p.m. |
| NER | Named-entity recognition | batch_69ff9e91bba08190af04b31ad815b13a |
completed | May 9, 2026, 8:52 p.m. |
| PD | Predicate disambiguation | batch_69ff9e00e4808190bde8f07e6519a72c |
completed | May 9, 2026, 8:50 p.m. |
| PDg | Predicate description generation | batch_69ff9e90b5248190bdd8d13f966b63e1 |
completed | May 9, 2026, 8:52 p.m. |
Created at: May 3, 2026, 4:03 p.m.