Triple

T8645017
Position Surface form Disambiguated ID Type / Status
Subject Sanamahism E204751 entity
Predicate hasDeity P5606 FINISHED
Object Umang Lai
Umang Lai are forest deities in the Meitei religion of Sanamahism, revered as guardians of sacred groves and natural spaces in Manipur.
E747894 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: Umang Lai | Statement: [Sanamahism, hasDeity, Umang Lai]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Umang Lai
Context triple: [Sanamahism, hasDeity, Umang Lai]
  • A. Umka
    Umka is a suburban settlement of Belgrade, Serbia, situated within the municipality of Čukarica along the right bank of the Sava River.
  • B. Yumani
    Yumani is a small lakeside village on Bolivia’s Isla del Sol, known as a main gateway for visitors and for its scenic views over Lake Titicaca.
  • C. Santoor
    Santoor is a popular Indian personal care brand best known for its sandalwood and turmeric-based bathing soaps.
  • D. Shila Ommi
    Shila Ommi is an Iranian-American actress known for her film, television, and voice roles, including work in major animated features.
  • E. Gaghan
    Gaghan is the surname of Stephen Gaghan, an American screenwriter and director known for works like "Traffic" and "Syriana."
  • 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: Umang Lai
Triple: [Sanamahism, hasDeity, Umang Lai]
Generated description
Umang Lai are forest deities in the Meitei religion of Sanamahism, revered as guardians of sacred groves and natural spaces in Manipur.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07
Target entity: Umang Lai
Target entity description: Umang Lai are forest deities in the Meitei religion of Sanamahism, revered as guardians of sacred groves and natural spaces in Manipur.
  • A. Umka
    Umka is a suburban settlement of Belgrade, Serbia, situated within the municipality of Čukarica along the right bank of the Sava River.
  • B. Yumani
    Yumani is a small lakeside village on Bolivia’s Isla del Sol, known as a main gateway for visitors and for its scenic views over Lake Titicaca.
  • C. Santoor
    Santoor is a popular Indian personal care brand best known for its sandalwood and turmeric-based bathing soaps.
  • D. Shila Ommi
    Shila Ommi is an Iranian-American actress known for her film, television, and voice roles, including work in major animated features.
  • E. Gaghan
    Gaghan is the surname of Stephen Gaghan, an American screenwriter and director known for works like "Traffic" and "Syriana."
  • 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_69ca834ca1c88190a11ffb0200342fac completed March 30, 2026, 2:06 p.m.
NER Named-entity recognition batch_69cc479999c881908c0c4e01c07d02d4 completed March 31, 2026, 10:15 p.m.
NED1 Entity disambiguation (via context triple) batch_69cebc42922c819099a464d2e347dec4 completed April 2, 2026, 6:58 p.m.
NEDg Description generation batch_69cec03fa5dc8190bbfe40aa1a3b27c1 completed April 2, 2026, 7:15 p.m.
NED2 Entity disambiguation (via description) batch_69cec0cac51c8190962a23d53c1fb48b completed April 2, 2026, 7:17 p.m.
Created at: March 30, 2026, 6:28 p.m.