Triple

T22244352
Position Surface form Disambiguated ID Type / Status
Subject HDI-Arena E549803 entity
Predicate formerName P65 FINISHED
Object AWD-Arena
AWD-Arena was the former name of the football stadium in Hanover, Germany, now known as the HDI-Arena and home to Hannover 96.
E1527485 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: AWD-Arena | Statement: [HDI-Arena, formerName, AWD-Arena]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: AWD-Arena
Context triple: [HDI-Arena, formerName, AWD-Arena]
  • A. ARENA
    ARENA is a major right-wing political party in El Salvador, known formally as the Nationalist Republican Alliance.
  • B. Arena 2000
    Arena 2000 is a modern multi-purpose indoor ice hockey arena in Yaroslavl, Russia, best known as the home venue of the Lokomotiv Yaroslavl hockey club.
  • C. Arena 13
    Arena 13 is a fantasy novel series by Joseph Delaney set in a brutal arena-combat world, distinct from but related to his Wardstone Chronicles universe.
  • D. Arenas
    Arenas is a Spanish-origin surname most notably associated with former NBA All-Star basketball player Gilbert Arenas.
  • E. Arenas
    Arenas is a competitive 3v3 round-based game mode in Apex Legends that focuses on small-scale, tactical combat outside the traditional battle royale format.
  • 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: AWD-Arena
Triple: [HDI-Arena, formerName, AWD-Arena]
Generated description
AWD-Arena was the former name of the football stadium in Hanover, Germany, now known as the HDI-Arena and home to Hannover 96.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07
Target entity: AWD-Arena
Target entity description: AWD-Arena was the former name of the football stadium in Hanover, Germany, now known as the HDI-Arena and home to Hannover 96.
  • A. ARENA
    ARENA is a major right-wing political party in El Salvador, known formally as the Nationalist Republican Alliance.
  • B. Arena 2000
    Arena 2000 is a modern multi-purpose indoor ice hockey arena in Yaroslavl, Russia, best known as the home venue of the Lokomotiv Yaroslavl hockey club.
  • C. Arena 13
    Arena 13 is a fantasy novel series by Joseph Delaney set in a brutal arena-combat world, distinct from but related to his Wardstone Chronicles universe.
  • D. Arenas
    Arenas is a Spanish-origin surname most notably associated with former NBA All-Star basketball player Gilbert Arenas.
  • E. Arenas
    Arenas is a competitive 3v3 round-based game mode in Apex Legends that focuses on small-scale, tactical combat outside the traditional battle royale format.
  • 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_69e11e41d9408190bd770cf282e22753 completed April 16, 2026, 5:37 p.m.
NER Named-entity recognition batch_69f132170e5081909b9dbb204abf2a45 completed April 28, 2026, 10:17 p.m.
NED1 Entity disambiguation (via context triple) batch_6a0ab65a809c8190be94c20c994dcdbb completed May 18, 2026, 6:48 a.m.
NEDg Description generation batch_6a0ab7f904bc81909addafee8773eae0 completed May 18, 2026, 6:55 a.m.
NED2 Entity disambiguation (via description) batch_6a0ab891ba1c81909c9e9a5f29d4eb54 completed May 18, 2026, 6:58 a.m.
Created at: April 16, 2026, 8:38 p.m.