Triple
T6969918
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Kavitrayam of Telugu Mahabharata |
E161573
|
entity |
| Predicate | collectiveNameFrom |
P36773
|
FINISHED |
| Object | Telugu word "Kavi" meaning poet |
—
|
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: Telugu word "Kavi" meaning poet | Statement: [Kavitrayam of Telugu Mahabharata, collectiveNameFrom, Telugu word "Kavi" meaning poet]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: collectiveNameFrom Context triple: [Kavitrayam of Telugu Mahabharata, collectiveNameFrom, Telugu word "Kavi" meaning poet]
-
A.
usedCollectiveName
Indicates that a group of entities is referred to by a shared collective name.
-
B.
collectivelyKnownAs
Indicates that multiple entities are referred to together under a single shared name or designation.
-
C.
commonNameOf
Indicates that one entity is the commonly used or popular name by which the other entity is known.
-
D.
nameComesFrom
chosen
Indicates that the name or designation of one entity is derived from, inspired by, or based on another entity.
-
E.
collectsFrom
Indicates that one entity gathers, receives, or takes something (such as items, data, or payments) from 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_69c68853cff881908439d488924a8283 |
completed | March 27, 2026, 1:38 p.m. |
| NER | Named-entity recognition | batch_69c6db1649288190a52c7dab57b3c7dc |
completed | March 27, 2026, 7:31 p.m. |
| PD | Predicate disambiguation | batch_69c6d7c262508190a7708b3d9cf23d7c |
completed | March 27, 2026, 7:17 p.m. |
Created at: March 27, 2026, 2:30 p.m.