Triple

T6420002
Position Surface form Disambiguated ID Type / Status
Subject Santhal E127920 entity
Predicate notableFestival P26210 FINISHED
Object Erok Sim
Erok Sim is a traditional festival celebrated by the Santhal community, reflecting their indigenous cultural and religious practices.
E592567 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: Erok Sim | Statement: [Santhal, notableFestival, Erok Sim]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Erok Sim
Context triple: [Santhal, notableFestival, Erok Sim]
  • A. Erikli
    Erikli is a Turkish bottled water brand known for its natural spring water, marketed under the Nestlé Waters portfolio.
  • B. Erik
    Erik is a masculine given name of Scandinavian origin that is widely used across various European countries.
  • C. Erik Neander
    Erik Neander is a Major League Baseball executive known for leading the Tampa Bay Rays’ front office and overseeing the club’s baseball operations and roster construction.
  • D. Erkki
    Erkki is a Finnish masculine given name commonly used as a variant of names like Eero or Erik.
  • E. Heino Ferch
    Heino Ferch is a German actor known for his versatile performances in film, television, and theater, often in historical and dramatic roles.
  • 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: Erok Sim
Triple: [Santhal, notableFestival, Erok Sim]
Generated description
Erok Sim is a traditional festival celebrated by the Santhal community, reflecting their indigenous cultural and religious practices.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07
Target entity: Erok Sim
Target entity description: Erok Sim is a traditional festival celebrated by the Santhal community, reflecting their indigenous cultural and religious practices.
  • A. Erikli
    Erikli is a Turkish bottled water brand known for its natural spring water, marketed under the Nestlé Waters portfolio.
  • B. Erik
    Erik is a masculine given name of Scandinavian origin that is widely used across various European countries.
  • C. Erik Neander
    Erik Neander is a Major League Baseball executive known for leading the Tampa Bay Rays’ front office and overseeing the club’s baseball operations and roster construction.
  • D. Erkki
    Erkki is a Finnish masculine given name commonly used as a variant of names like Eero or Erik.
  • E. Heino Ferch
    Heino Ferch is a German actor known for his versatile performances in film, television, and theater, often in historical and dramatic roles.
  • 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_69c0083815208190a9b299b8e0640218 completed March 22, 2026, 3:18 p.m.
NER Named-entity recognition batch_69c06902ddb48190bd5a8b5ecdf6c39e completed March 22, 2026, 10:11 p.m.
NED1 Entity disambiguation (via context triple) batch_69c640d5f6f88190963a1e59400c7aa0 completed March 27, 2026, 8:33 a.m.
NEDg Description generation batch_69c6428e44108190b7cb592a05b4acbb completed March 27, 2026, 8:40 a.m.
NED2 Entity disambiguation (via description) batch_69c64343c19c8190b05ef4450aadcbd1 completed March 27, 2026, 8:43 a.m.
Created at: March 22, 2026, 4:43 p.m.