Triple

T19572009
Position Surface form Disambiguated ID Type / Status
Subject Joe Dirt E489739 entity
Predicate character P662 FINISHED
Object Kicking Wing
Kicking Wing is a Native American fireworks salesman and friend of the title character in the comedy film "Joe Dirt."
 E1382967 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: Kicking Wing | Statement: [Joe Dirt, character, Kicking Wing]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07 
Target entity: Kicking Wing
Context triple: [Joe Dirt, character, Kicking Wing]
  • A. Wild Wing
    Wild Wing is the anthropomorphic duck mascot of the NHL's Anaheim Ducks, known for his energetic in-game antics and appearances at team events.
  • B. The Wing
    The Wing was a women-focused co-working and community space network known for its stylish, inclusive hubs designed to support professional women and gender-expansive people.
  • C. Wing
    Wing is an experimental mobile operating system and user interface project developed by X (formerly Google X) to explore new paradigms in smartphone interaction and design.
  • D. Wing
    Wing is an Alphabet Inc. subsidiary focused on developing and operating drone-based delivery services and related logistics technologies.
  • E. Wing
    Wing is a Japanese lingerie and intimate apparel brand known for its comfortable, everyday undergarments for women.
  • 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: Kicking Wing
Triple: [Joe Dirt, character, Kicking Wing]
Generated description
Kicking Wing is a Native American fireworks salesman and friend of the title character in the comedy film "Joe Dirt."
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07 
Target entity: Kicking Wing
Target entity description: Kicking Wing is a Native American fireworks salesman and friend of the title character in the comedy film "Joe Dirt."
  • A. Wild Wing
    Wild Wing is the anthropomorphic duck mascot of the NHL's Anaheim Ducks, known for his energetic in-game antics and appearances at team events.
  • B. The Wing
    The Wing was a women-focused co-working and community space network known for its stylish, inclusive hubs designed to support professional women and gender-expansive people.
  • C. Wing
    Wing is an experimental mobile operating system and user interface project developed by X (formerly Google X) to explore new paradigms in smartphone interaction and design.
  • D. Wing
    Wing is a record label imprint associated with the release of the song "Feels Good."
  • E. Wing
    Wing is an Alphabet Inc. subsidiary focused on developing and operating drone-based delivery services and related logistics technologies.
  • 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_69d8e8dd9374819098e36349b3211663 completed April 10, 2026, 12:11 p.m.
NER Named-entity recognition batch_69e6402103208190b80acdfa82b7a9c4 completed April 20, 2026, 3:02 p.m.
NED1 Entity disambiguation (via context triple) batch_6a07578dc3c08190aeddf81b69afe055 completed May 15, 2026, 5:27 p.m.
NEDg Description generation batch_6a0758751d0c8190a5e150d5a093f51a completed May 15, 2026, 5:31 p.m.
NED2 Entity disambiguation (via description) batch_6a0758e997bc8190a32977d1810e4aeb completed May 15, 2026, 5:33 p.m.
Created at: April 10, 2026, 1:42 p.m.