Triple

T14767979
Position Surface form Disambiguated ID Type / Status
Subject Harrisburg Heat E347049 entity
Predicate shortName P43 FINISHED
Object Heat
Heat is an American professional indoor soccer team based in Harrisburg, Pennsylvania, competing in the Major Arena Soccer League.
 E1118729 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: Heat | Statement: [Harrisburg Heat, shortName, Heat]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07 
Target entity: Heat
Context triple: [Harrisburg Heat, shortName, Heat]
  • A. Heat
    Heat is a 1995 crime thriller film directed by Michael Mann, renowned for its intense heist sequences and the iconic pairing of Al Pacino and Robert De Niro.
  • B. Heat
    Heat is a chapter or section within the novel "Like Water for Chocolate" that focuses on themes of passion, desire, and emotional intensity.
  • C. Heat
    Heat is OpenStack’s orchestration service that automates the deployment and management of cloud infrastructure using template-based definitions.
  • D. Heat
    Heat is a 1963 Soviet drama film directed by Larisa Shepitko, marking her acclaimed feature-length directorial debut.
  • E. Heat
    Heat is a professional Twenty20 cricket team based in Brisbane that competes in Australia's Big Bash League.
  • 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: Heat
Triple: [Harrisburg Heat, shortName, Heat]
Generated description
Heat is an American professional indoor soccer team based in Harrisburg, Pennsylvania, competing in the Major Arena Soccer League.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07 
Target entity: Heat
Target entity description: Heat is an American professional indoor soccer team based in Harrisburg, Pennsylvania, competing in the Major Arena Soccer League.
  • A. Heat
    Heat is a professional Twenty20 cricket team based in Brisbane that competes in Australia's Big Bash League.
  • B. Heat
    Heat is a 1972 American underground film directed by Paul Morrissey and produced by Andy Warhol, known for its satirical take on Hollywood and its place within the Warhol Factory film movement.
  • C. Heat
    Heat is a 1995 crime thriller film directed by Michael Mann, renowned for its intense heist sequences and the iconic pairing of Al Pacino and Robert De Niro.
  • D. Heat
    Heat is a chapter or section within the novel "Like Water for Chocolate" that focuses on themes of passion, desire, and emotional intensity.
  • E. Heat
    Heat is OpenStack’s orchestration service that automates the deployment and management of cloud infrastructure using template-based definitions.
  • 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_69d822e8896c819091169882f9b20486 completed April 9, 2026, 10:06 p.m.
NER Named-entity recognition batch_69dec81236f081908063bb4350b7b985 completed April 14, 2026, 11:04 p.m.
NED1 Entity disambiguation (via context triple) batch_69fe0cf86730819082cf3f502ec16a46 completed May 8, 2026, 4:19 p.m.
NEDg Description generation batch_69fe1874682881909ff97bca55bea320 completed May 8, 2026, 5:08 p.m.
NED2 Entity disambiguation (via description) batch_69fe1918fa988190b8ed746aa6f6f829 completed May 8, 2026, 5:10 p.m.
Created at: April 10, 2026, 1:30 a.m.