Triple
T4111448
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Ken Arok |
E88582
|
entity |
| Predicate | successor |
P78
|
FINISHED |
| Object | Anusapati |
E88584
|
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: Anusapati | Statement: [Ken Arok, successor, Anusapati]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Anusapati Context triple: [Ken Arok, successor, Anusapati]
-
A.
Anusapati
chosen
Anusapati was a 13th-century Javanese king who ruled the Singhasari Kingdom in East Java, Indonesia.
-
B.
Wiradhuri
Wiradhuri refers to the Wiradjuri people, one of the largest Aboriginal groups in New South Wales, Australia, known for their rich cultural traditions and strong connection to the land.
-
C.
Tarapith
Tarapith is a renowned Hindu pilgrimage town in India famous for its temple dedicated to the goddess Tara and associated tantric practices.
-
D.
Saketa
Saketa is the ancient name of the historic Indian city now known as Ayodhya, a major cultural and religious center in Hindu tradition.
-
E.
Santalī
Santalī is an Austroasiatic language spoken primarily by the Santal people in eastern India, Bangladesh, Nepal, and Bhutan.
- 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_69aed9484fb881909146f4c772ad277c |
completed | March 9, 2026, 2:29 p.m. |
| NER | Named-entity recognition | batch_69af01dd7140819093d3332eb94a357c |
completed | March 9, 2026, 5:22 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69b56b8adc748190be7b34ff37ae3618 |
completed | March 14, 2026, 2:07 p.m. |
Created at: March 9, 2026, 3:41 p.m.