Triple
T23010595
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | RY |
E572893
|
entity |
| Predicate | hasAnalystCoverage |
P8698
|
FINISHED |
| Object | true |
—
|
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: true | Statement: [RY, hasAnalystCoverage, true]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: hasAnalystCoverage Context triple: [RY, hasAnalystCoverage, true]
-
A.
hasNotableAnalyst
chosen
Indicates that an entity is associated with an analyst who is recognized as particularly important, influential, or noteworthy in relation to that entity.
-
B.
hasCreditRatingAgencyCoverage
Indicates that an entity is monitored, evaluated, or rated by a credit rating agency.
-
C.
marketCovered
Indicates that one entity’s products or services are already available or served within the geographic or customer market associated with another entity.
-
D.
hasMarketSurveillance
Indicates that an entity performs or is subject to ongoing monitoring and oversight of market activities to detect irregularities or non-compliance.
-
E.
hasPublisherCoverage
Indicates that a publisher provides content, services, or distribution that extend over or apply to a specified entity or area.
- 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_69e245b764cc8190a51be76f1d9611e1 |
completed | April 17, 2026, 2:37 p.m. |
| NER | Named-entity recognition | batch_69f18359f5548190b15a139eb09e30a0 |
completed | April 29, 2026, 4:04 a.m. |
| PD | Predicate disambiguation | batch_69ef3b9cd5488190bcd23183179f48cd |
completed | April 27, 2026, 10:34 a.m. |
Created at: April 17, 2026, 3:51 p.m.