Triple

T22244365
Position Surface form Disambiguated ID Type / Status
Subject HDI-Arena E549803 entity
Predicate sponsor P67 FINISHED
Object HDI
HDI is a German insurance and financial services company that sponsors various sports venues and events.
 E1527487 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: HDI | Statement: [HDI-Arena, sponsor, HDI]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07 
Target entity: HDI
Context triple: [HDI-Arena, sponsor, HDI]
  • A. HDI
    The HDI is a composite statistic used by the United Nations to measure and compare countries’ overall human development based on health, education, and standard of living.
  • B. Hdi
    Hdi is a Central Chadic language spoken primarily in northern Cameroon and nearby areas of Nigeria.
  • C. HD1
    HD1 was a French television channel that later became known as TF1 Séries Films, focusing on series and film programming.
  • D. HCD
    HCD is the California state agency responsible for housing policy, affordable housing programs, and community development initiatives.
  • E. HCD
    HCD is the common abbreviation for HC Davos, a professional ice hockey club based in Davos, Switzerland.
  • 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: HDI
Triple: [HDI-Arena, sponsor, HDI]
Generated description
HDI is a German insurance and financial services company that sponsors various sports venues and events.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07 
Target entity: HDI
Target entity description: HDI is a German insurance and financial services company that sponsors various sports venues and events.
  • A. HDI
    The HDI is a composite statistic used by the United Nations to measure and compare countries’ overall human development based on health, education, and standard of living.
  • B. Hdi
    Hdi is a Central Chadic language spoken primarily in northern Cameroon and nearby areas of Nigeria.
  • C. HD1
    HD1 was a French television channel that later became known as TF1 Séries Films, focusing on series and film programming.
  • D. HCD
    HCD is the California state agency responsible for housing policy, affordable housing programs, and community development initiatives.
  • E. HCD
    HCD is the common abbreviation for HC Davos, a professional ice hockey club based in Davos, Switzerland.
  • 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.