Triple

T19595631
Position Surface form Disambiguated ID Type / Status
Subject Phra Ram E470340 entity
Predicate enemy P4567 FINISHED
Object Totsakan 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: Totsakan | Statement: [Phra Ram, enemy, Totsakan]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Totsakan
Context triple: [Phra Ram, enemy, Totsakan]
  • A. Totsakan chosen
    Totsakan is the ten-headed demon king of Lanka in the Thai epic Ramakien, serving as its central villain and a key figure in Thai classical literature and performance.
  • B. Takanot
    Takanot are rabbinic enactments or decrees established to address communal needs and clarify or safeguard Jewish law within Rabbinic Judaism.
  • C. Takaro
    Takaro is a residential suburb located within the city of Palmerston North in New Zealand.
  • D. Taketa
    Taketa is a small historic city in Japan known for its scenic rural landscapes, hot springs, and castle ruins.
  • E. Takabisha
    Takabisha is a record-breaking steel roller coaster in Japan renowned for its extremely steep drop and intense thrill elements.
  • 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_69d8e510024481908415c0d616fa6186 completed April 10, 2026, 11:54 a.m.
NER Named-entity recognition batch_69e6407a09608190aa1df92f8c21f9e7 completed April 20, 2026, 3:04 p.m.
Created at: April 10, 2026, 1:43 p.m.