Triple

T22711278
Position Surface form Disambiguated ID Type / Status
Subject NK Osijek E561605 entity
Predicate league P888 FINISHED
Object HNL
HNL is the top professional football league in Croatia, featuring the country's leading clubs in its premier competition.
E1550293 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: HNL | Statement: [NK Osijek, league, HNL]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: HNL
Context triple: [NK Osijek, league, HNL]
  • A. HNL
    HNL is the IATA airport code for Daniel K. Inouye International Airport, the primary commercial airport serving Honolulu and the state of Hawaii.
  • B. HNL
    HNL is the currency code for the Honduran lempira, the official monetary unit of Honduras.
  • C. Hawi
    Hawi is a small historic town on the northern tip of Hawaii’s Big Island, known as a gateway to the Kohala region and for its charming shops and scenic coastal views.
  • D. Haʻano
    Haʻano is a small inhabited island in the Haʻapai group of Tonga, known for its traditional villages and quiet, rural character.
  • E. Nukulaelae
    Nukulaelae is one of the small coral atolls of Tuvalu in the central Pacific Ocean, home to a traditional Tuvaluan community and culture.
  • 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: HNL
Triple: [NK Osijek, league, HNL]
Generated description
HNL is the top professional football league in Croatia, featuring the country's leading clubs in its premier competition.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07
Target entity: HNL
Target entity description: HNL is the top professional football league in Croatia, featuring the country's leading clubs in its premier competition.
  • A. HNL
    HNL is the IATA airport code for Daniel K. Inouye International Airport, the primary commercial airport serving Honolulu and the state of Hawaii.
  • B. HNL
    HNL is the currency code for the Honduran lempira, the official monetary unit of Honduras.
  • C. Hawi
    Hawi is a small historic town on the northern tip of Hawaii’s Big Island, known as a gateway to the Kohala region and for its charming shops and scenic coastal views.
  • D. Haʻano
    Haʻano is a small inhabited island in the Haʻapai group of Tonga, known for its traditional villages and quiet, rural character.
  • E. Nukulaelae
    Nukulaelae is one of the small coral atolls of Tuvalu in the central Pacific Ocean, home to a traditional Tuvaluan community and culture.
  • 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_69e2454f1348819088d83f420925a5c1 completed April 17, 2026, 2:35 p.m.
NER Named-entity recognition batch_69f17907d7288190bb53f76974f95cef completed April 29, 2026, 3:20 a.m.
NED1 Entity disambiguation (via context triple) batch_6a0b7ed9cb908190b50dd5297ca2d17c completed May 18, 2026, 9:04 p.m.
NEDg Description generation batch_6a0b7fbb53388190b0942c28b5748c60 completed May 18, 2026, 9:08 p.m.
NED2 Entity disambiguation (via description) batch_6a0b806b4e1481909babc97a8914947a completed May 18, 2026, 9:11 p.m.
Created at: April 17, 2026, 3:18 p.m.