Triple
T18644116
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Kali Mata |
E455760
|
entity |
| Predicate | otherName |
P39
|
FINISHED |
| Object | Kalika |
—
|
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: Kalika | Statement: [Kali Mata, otherName, Kalika]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Kalika Context triple: [Kali Mata, otherName, Kalika]
-
A.
Mandodari
Mandodari is a revered queen in the Hindu epic Ramayana, known as the wise and virtuous wife of the demon king Ravana.
-
B.
Kartika
Kartika is a significant autumn month in the traditional Odia lunar calendar, often associated with religious observances and festivals.
-
C.
Lalita
Lalita is a revered aspect of the Hindu goddess Devi, celebrated as a beautiful, benevolent, and playful form of the Divine Mother often associated with Sri Vidya worship.
-
D.
Lady Shiva
Lady Shiva is a deadly martial artist and assassin in DC Comics, renowned as one of the most skilled hand-to-hand combatants in the world and often connected to the Batman family.
-
E.
Kali
chosen
Kali is a fierce and powerful Hindu goddess associated with time, destruction, and the transformative power that annihilates evil.
- 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_69d8d38ea1e88190997e9b231190ba6f |
completed | April 10, 2026, 10:40 a.m. |
| NER | Named-entity recognition | batch_69e5500c36188190bfdd7aca73f3c006 |
completed | April 19, 2026, 9:58 p.m. |
Created at: April 10, 2026, 11:47 a.m.