Triple
T36687683
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Kavirajamarga |
E905866
|
entity |
| Predicate | probableAuthor |
P13198
|
FINISHED |
| Object | Sri Vijaya |
—
|
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: Sri Vijaya | Statement: [Kavirajamarga, probableAuthor, Sri Vijaya]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: probableAuthor Context triple: [Kavirajamarga, probableAuthor, Sri Vijaya]
-
A.
probableAuthorOf
chosen
Indicates that an entity is likely, but not certainly, the author or creator of another entity.
-
B.
favoriteAuthor
Indicates that one entity is the author whom another entity prefers above all others.
-
C.
authorFounded
Indicates that the author is the person who established or created the referenced organization, institution, or entity.
-
D.
canonicalAuthor
Indicates that an entity is the officially recognized or standard author of a given work or resource.
-
E.
authoredWith
Indicates that two or more entities jointly created or wrote a work together.
- 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_69f76e70d2448190bdd3ce781ba971c5 |
completed | May 3, 2026, 3:49 p.m. |
| NER | Named-entity recognition | batch_69f7c7c5dc0081908f0e289286853c3d |
completed | May 3, 2026, 10:10 p.m. |
| PD | Predicate disambiguation | batch_69f7c4796ebc819084a0dc08505e5f14 |
completed | May 3, 2026, 9:56 p.m. |
Created at: May 3, 2026, 4:12 p.m.