Triple
T8549942
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Madhavi |
E202419
|
entity |
| Predicate | roleInSilappatikaram |
P11527
|
FINISHED |
| Object | courtesan beloved of Kovalan |
—
|
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: courtesan beloved of Kovalan | Statement: [Madhavi, roleInSilappatikaram, courtesan beloved of Kovalan]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: roleInSilappatikaram Context triple: [Madhavi, roleInSilappatikaram, courtesan beloved of Kovalan]
-
A.
roleInNyaya
Indicates that one entity holds a specific philosophical or logical role within the Nyaya school or framework in relation to another entity.
-
B.
roleInTheology
Indicates the specific function, position, or significance an entity holds within a theological system, doctrine, or belief framework.
-
C.
roleInText
chosen
Indicates that an entity participates in a text with a specific function or capacity (e.g., author, editor, character).
-
D.
legalCaseRole
Indicates the specific role or capacity an entity holds within a legal case, such as plaintiff, defendant, judge, or attorney.
-
E.
roleInKojiki
Indicates the role or function an entity holds within the narrative or structure of the Kojiki.
- 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_69ca832610e08190b3b6c6cd2c250255 |
completed | March 30, 2026, 2:05 p.m. |
| NER | Named-entity recognition | batch_69cbe75589d8819096177ddbd3dafcb6 |
completed | March 31, 2026, 3:25 p.m. |
| PD | Predicate disambiguation | batch_69cbd113e05c81908f4f3fc1b5925164 |
completed | March 31, 2026, 1:50 p.m. |
Created at: March 30, 2026, 6:19 p.m.