Triple
T32480404
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Pahari (Jammu) |
E830090
|
entity |
| Predicate | nameAlsoAppliedTo |
P82190
|
FINISHED |
| Object | other Pahari languages of the Himalayas |
—
|
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: other Pahari languages of the Himalayas | Statement: [Pahari (Jammu), nameAlsoAppliedTo, other Pahari languages of the Himalayas]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: nameAlsoAppliedTo Context triple: [Pahari (Jammu), nameAlsoAppliedTo, other Pahari languages of the Himalayas]
-
A.
nameAppliesTo
chosen
Indicates that a particular name is assigned to, or valid for use with, a specific entity.
-
B.
appliesAlsoTo
Indicates that a condition, rule, or characteristic that applies to one entity is additionally applicable to another entity.
-
C.
previouslyAppliedTo
Indicates that an entity has submitted an application to another entity at some earlier time in the past.
-
D.
associatedName
Indicates that one entity has an alternative or related name that is linked or connected to another entity.
-
E.
appliedFrom
Indicates that an application or request was initiated starting at or originating from a particular source, location, or context.
- 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_69f3491ff3b48190b50a7fa00bb05b1f |
completed | April 30, 2026, 12:20 p.m. |
| NER | Named-entity recognition | batch_69f6c395640c81908808b2d4d40f26e7 |
completed | May 3, 2026, 3:40 a.m. |
| PD | Predicate disambiguation | batch_69f6bd25bed08190befcabd3a41ffadf |
completed | May 3, 2026, 3:12 a.m. |
Created at: May 1, 2026, 12:58 a.m.