Triple
T8564593
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Cilappatikāram |
E202771
|
entity |
| Predicate | includesCharacter |
P5716
|
FINISHED |
| Object | Madhavi |
E202419
|
NE 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: Madhavi | Statement: [Cilappatikāram, includesCharacter, Madhavi]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Madhavi Context triple: [Cilappatikāram, includesCharacter, Madhavi]
-
A.
Madhavi
chosen
Madhavi is a celebrated courtesan and pivotal literary figure in ancient Tamil epic tradition, prominently featured in the Sangam-era works Silappatikaram and its sequel Manimekalai.
-
B.
Anjali
Anjali is an Indian pediatrician best known as the wife of legendary cricketer Sachin Tendulkar.
-
C.
Shilpa
Shilpa is a pivotal transgender character in the Tamil film "Super Deluxe," known for her complex portrayal and emotional depth.
-
D.
Revati
Revati is a princess from Hindu mythology, known as the daughter of King Kakudmi and the wife of the deity Balarama.
-
E.
Aparna
Aparna is a central character in Satyajit Ray’s film "Apur Sansar," portrayed as Apu’s wife whose relationship with him profoundly shapes the emotional core of the story.
- F. None of above.
- G. Unsure - the case is ambiguous/there is not enough information to decide.
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_69ca8326e6c881908ff720d6abaebdc5 |
completed | March 30, 2026, 2:05 p.m. |
| NER | Named-entity recognition | batch_69cbe9d11274819099cc33a21a993a1f |
completed | March 31, 2026, 3:35 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69cebb84a6988190ba6852f72c8918ca |
completed | April 2, 2026, 6:55 p.m. |
Created at: March 30, 2026, 6:20 p.m.