Triple

T19595692
Position Surface form Disambiguated ID Type / Status
Subject Totsakan E470341 entity
Predicate hasVariantName P457 FINISHED
Object Tosakanth
Tosakanth is a giant demon king from the Thai Ramakien epic, adapted from the character Ravana in the Indian Ramayana.
E1385945 NE FINISHED

How this triple was built (4 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: Tosakanth | Statement: [Totsakan, hasVariantName, Tosakanth]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Tosakanth
Context triple: [Totsakan, hasVariantName, Tosakanth]
  • A. Tosora
    Tosora is a historic town in South Sulawesi, Indonesia, known as the former political and cultural center of the Bugis Kingdom of Wajo.
  • B. Takanot
    Takanot are rabbinic enactments or decrees established to address communal needs and clarify or safeguard Jewish law within Rabbinic Judaism.
  • C. Tahkuna
    Tahkuna is a coastal settlement in northern Estonia, located on Hiiumaa Island and known for its proximity to the historic Tahkuna Lighthouse.
  • D. Tosiwo
    Tosiwo is a given name most notably borne by Tosiwo Nakayama, the first President of the Federated States of Micronesia.
  • E. Tokoro
    Tokoro is a coastal district of Kitami City in Hokkaido, Japan, known historically for its fishing industry and drift ice along the Sea of Okhotsk.
  • F. None of above. chosen
  • G. Unsure - the case is ambiguous/there is not enough information to decide.
NEDg Description generation gpt-5.1
Instruction
Generate a one-sentence description of the target entity. 
You are given a context triple in the form (subject, predicate, object), where the object is the target entity. 
# Instructions
Use the triple to infer relevant information about the entity. Describe the entity based on what is most defining, well-known. 
Avoid repeating the information from the triple, unless really essential.
# Response Format
Return only the sentence: "Description: [one-sentence description of the target entity]"
Input
Entity: Tosakanth
Triple: [Totsakan, hasVariantName, Tosakanth]
Generated description
Tosakanth is a giant demon king from the Thai Ramakien epic, adapted from the character Ravana in the Indian Ramayana.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07
Target entity: Tosakanth
Target entity description: Tosakanth is a giant demon king from the Thai Ramakien epic, adapted from the character Ravana in the Indian Ramayana.
  • A. Tosora
    Tosora is a historic town in South Sulawesi, Indonesia, known as the former political and cultural center of the Bugis Kingdom of Wajo.
  • B. Takanot
    Takanot are rabbinic enactments or decrees established to address communal needs and clarify or safeguard Jewish law within Rabbinic Judaism.
  • C. Tahkuna
    Tahkuna is a coastal settlement in northern Estonia, located on Hiiumaa Island and known for its proximity to the historic Tahkuna Lighthouse.
  • D. Tosiwo
    Tosiwo is a given name most notably borne by Tosiwo Nakayama, the first President of the Federated States of Micronesia.
  • E. Tokoro
    Tokoro is a coastal district of Kitami City in Hokkaido, Japan, known historically for its fishing industry and drift ice along the Sea of Okhotsk.
  • F. None of above. chosen

Provenance (5 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.
NED1 Entity disambiguation (via context triple) batch_6a0771ab9d548190841ef3bce61c3571 completed May 15, 2026, 7:19 p.m.
NEDg Description generation batch_6a07728da308819098af49160af0f1e0 completed May 15, 2026, 7:22 p.m.
NED2 Entity disambiguation (via description) batch_6a0772e394fc8190b96fe74de6f5fdea completed May 15, 2026, 7:24 p.m.
Created at: April 10, 2026, 1:43 p.m.