Triple
T9809081
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | PHAT |
E238222
|
entity |
| Predicate | filterCoverage |
P14568
|
FINISHED |
| Object | multiple broad-band filters |
—
|
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: multiple broad-band filters | Statement: [PHAT, filterCoverage, multiple broad-band filters]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: filterCoverage Context triple: [PHAT, filterCoverage, multiple broad-band filters]
-
A.
formatCoverage
Indicates how thoroughly or extensively a particular format or formatting scheme is applied or supported in a given context.
-
B.
componentCoverage
Indicates that one entity provides coverage, protection, or support for another as one of its components or constituent parts.
-
C.
hasCoverageFocus
Indicates that one entity’s coverage, attention, or analysis is specifically focused on or directed toward another entity.
-
D.
coverageScope
chosen
Indicates the extent or range of entities, conditions, or situations that are included under a particular coverage or applicability.
-
E.
impliesCoverage
Indicates that one entity’s scope, protection, or applicability extends to or includes another entity.
- 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_69ca84defac48190abc1148804f184c1 |
completed | March 30, 2026, 2:12 p.m. |
| NER | Named-entity recognition | batch_69cdb21ef32c8190ab4b09d157798451 |
completed | April 2, 2026, 12:02 a.m. |
| PD | Predicate disambiguation | batch_69cd03dd2da881909052fbf29736a773 |
completed | April 1, 2026, 11:39 a.m. |
Created at: March 30, 2026, 8:29 p.m.