Triple

T23071545
Position Surface form Disambiguated ID Type / Status
Subject Polska Hokej Liga E575208 entity
Predicate abbreviation P43 FINISHED
Object PHL
PHL is the top professional ice hockey league in Poland, featuring the country’s leading clubs and players.
 E1569468 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: PHL | Statement: [Polska Hokej Liga, abbreviation, PHL]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07 
Target entity: PHL
Context triple: [Polska Hokej Liga, abbreviation, PHL]
  • A. PHL
    PHL is the three-letter IATA airport code for Philadelphia International Airport, the primary commercial airport serving the Philadelphia metropolitan area in Pennsylvania, USA.
  • B. PHL
    PHL is the three-letter country code for the Philippines, a Southeast Asian nation in the western Pacific Ocean.
  • C. PHI
    PHI is a helicopter services company, formally known as PHI, Inc., that provides aviation support primarily to the oil and gas industry and for air medical transport.
  • D. PHI
    PHI refers to the Philadelphia Eagles, a professional American football team based in Philadelphia that competes in the NFL.
  • E. PHI
    PHI is a scientific instrument designed to study the Sun’s magnetic fields and internal structure using polarimetric and helioseismic measurements.
  • 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: PHL
Triple: [Polska Hokej Liga, abbreviation, PHL]
Generated description
PHL is the top professional ice hockey league in Poland, featuring the country’s leading clubs and players.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07 
Target entity: PHL
Target entity description: PHL is the top professional ice hockey league in Poland, featuring the country’s leading clubs and players.
  • A. PHL
    PHL is the three-letter IATA airport code for Philadelphia International Airport, the primary commercial airport serving the Philadelphia metropolitan area in Pennsylvania, USA.
  • B. PHL
    PHL is the three-letter country code for the Philippines, a Southeast Asian nation in the western Pacific Ocean.
  • C. PHI
    PHI is a helicopter services company, formally known as PHI, Inc., that provides aviation support primarily to the oil and gas industry and for air medical transport.
  • D. PHI
    PHI is a scientific instrument designed to study the Sun’s magnetic fields and internal structure using polarimetric and helioseismic measurements.
  • E. PHI
    PHI refers to the Philadelphia Eagles, a professional American football team based in Philadelphia that competes in the NFL.
  • 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_69e245bd6e4c8190bb8942245b68cad5 completed April 17, 2026, 2:37 p.m.
NER Named-entity recognition batch_69f18c5ffad881909ed626045c15dd33 completed April 29, 2026, 4:43 a.m.
NED1 Entity disambiguation (via context triple) batch_6a0c15a941748190b6c44e4a6e6256e2 completed May 19, 2026, 7:47 a.m.
NEDg Description generation batch_6a0c1647dc2881909ee6c13b48b71b8d completed May 19, 2026, 7:50 a.m.
NED2 Entity disambiguation (via description) batch_6a0c187f6eec81909cf9a62835d56391 completed May 19, 2026, 7:59 a.m.
Created at: April 17, 2026, 3:56 p.m.