Triple
T18884286
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Kayadhu |
E461917
|
entity |
| Predicate | relatedTo |
P37
|
FINISHED |
| Object | Holika |
—
|
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: Holika | Statement: [Kayadhu, relatedTo, Holika]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Holika Context triple: [Kayadhu, relatedTo, Holika]
-
A.
Holika
chosen
Holika is a demoness from Hindu mythology, known for her failed attempt to kill her devout nephew Prahlada by fire and for being central to the legend behind the Holi festival.
-
B.
Mandodari
Mandodari is a revered queen in the Hindu epic Ramayana, known as the wise and virtuous wife of the demon king Ravana.
-
C.
Hudra
The Hudra is a principal liturgical book of the Syriac tradition, containing prayers, hymns, and rites used throughout the liturgical year.
-
D.
Mahishya
Mahishya is a prominent agrarian and artisan community from Bengal, historically influential in regional society, economy, and social reform movements.
-
E.
Bholath
Bholath is a small town in the Kapurthala district of the Indian state of Punjab, known primarily as a local administrative and market center for surrounding rural areas.
- 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_69d8dcfc3430819095ee6fc0eb4c06a5 |
completed | April 10, 2026, 11:20 a.m. |
| NER | Named-entity recognition | batch_69e5c3d3dcec8190a468162c6a4482f6 |
completed | April 20, 2026, 6:12 a.m. |
Created at: April 10, 2026, 11:57 a.m.