Triple
T20649534
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Kaanum Thirunaal |
E507449
|
entity |
| Predicate | alsoKnownAs |
P39
|
FINISHED |
| Object | Kaanum Pandigai |
—
|
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: Kaanum Pandigai | Statement: [Kaanum Thirunaal, alsoKnownAs, Kaanum Pandigai]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Kaanum Pandigai Context triple: [Kaanum Thirunaal, alsoKnownAs, Kaanum Pandigai]
-
A.
Kaanum Thirunaal
chosen
Kaanum Thirunaal is a Tamil festival day, observed as the concluding celebration of the Pongal harvest festival, marked by family outings, social visits, and communal gatherings.
-
B.
Pandianadu
Pandianadu is a Tamil-language action drama film known for its rural setting and intense storytelling, featuring filmmaker Bharathiraja in an acting role.
-
C.
Ponnji
Ponnji is an alternate local name for Panaji, the capital city of the Indian state of Goa known for its riverside setting and Portuguese-influenced architecture.
-
D.
Mullaippāṭṭu
Mullaippāṭṭu is a classical Tamil poem from the Sangam era, celebrated for its depiction of love and separation set against a pastoral landscape.
-
E.
Velaikkaran
Velaikkaran is a 2017 Tamil-language social drama film starring Sivakarthikeyan that focuses on corporate corruption and the struggles of exploited workers.
- F. None of above.
- G. Unsure - the case is ambiguous/there is not enough information to decide.
Provenance (2 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_69e0b4bf58c081908e52a4500e03ff83 |
completed | April 16, 2026, 10:06 a.m. |
| NER | Named-entity recognition | batch_69e6af2076b48190b9c8afb4eac65f46 |
completed | April 20, 2026, 10:56 p.m. |
Created at: April 16, 2026, 11:43 a.m.