Triple
T31645270
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Arabhi |
E807567
|
entity |
| Predicate | languageOfManyCompositions |
P60621
|
FINISHED |
| Object | Telugu |
—
|
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: Telugu | Statement: [Arabhi, languageOfManyCompositions, Telugu]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: languageOfManyCompositions Context triple: [Arabhi, languageOfManyCompositions, Telugu]
-
A.
languageOfWritings
Indicates that a specified language is the one in which certain writings or written works are composed.
-
B.
languageOfMusic
Indicates that a specified language is used in, associated with, or characteristic of a particular piece of music or musical work.
-
C.
compositionalLanguage
Indicates that one language is constructed from or systematically built upon elements, rules, or structures of another language.
-
D.
wroteInMultipleLanguages
Indicates that an entity authored written works using more than one language.
-
E.
repertoireLanguage
chosen
Indicates that the associated entity’s repertoire (e.g., works, performances, or outputs) is expressed or available in a particular language.
- 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_69f348d9ce58819093ea2da83cbeeec1 |
completed | April 30, 2026, 12:19 p.m. |
| NER | Named-entity recognition | batch_69ff90b673248190b4dda9e005642d17 |
completed | May 9, 2026, 7:53 p.m. |
| PD | Predicate disambiguation | batch_69ff8d5bee1081909274052945e98a6f |
completed | May 9, 2026, 7:39 p.m. |
Created at: April 30, 2026, 10:50 p.m.