Triple

T9695465
Position Surface form Disambiguated ID Type / Status
Subject Scott Lang E234637 entity
Predicate friend P8712 FINISHED
Object Kurt
Kurt is a close associate of Scott Lang in the Marvel universe, known as one of his quirky ex-con partners in crime and heists.
E815842 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: Kurt | Statement: [Scott Lang, friend, Kurt]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Kurt
Context triple: [Scott Lang, friend, Kurt]
  • A. Kurt
    Kurt is a given name most famously associated with the logician and mathematician Kurt Gödel.
  • B. Kurt Christian
    Kurt Christian is a British actor best known for his roles in 1970s fantasy and adventure films, particularly in Ray Harryhausen–associated productions.
  • C. Kurt Weiss
    Kurt Weiss is an individual notable enough to be recognized as a namesake of the surname Weiss, though specific widely known biographical details are not clearly established.
  • D. Kurt Back
    Kurt Back was a social psychologist known for his collaborative research in social behavior and group dynamics, including work with Leon Festinger.
  • E. Karl
    Karl is the given first name of Charles Proteus Steinmetz, the renowned German-American mathematician and electrical engineer who revolutionized the understanding of alternating current systems.
  • 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: Kurt
Triple: [Scott Lang, friend, Kurt]
Generated description
Kurt is a close associate of Scott Lang in the Marvel universe, known as one of his quirky ex-con partners in crime and heists.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07
Target entity: Kurt
Target entity description: Kurt is a close associate of Scott Lang in the Marvel universe, known as one of his quirky ex-con partners in crime and heists.
  • A. Kurt
    Kurt is a given name most famously associated with the logician and mathematician Kurt Gödel.
  • B. Kurt Christian
    Kurt Christian is a British actor best known for his roles in 1970s fantasy and adventure films, particularly in Ray Harryhausen–associated productions.
  • C. Kurt Weiss
    Kurt Weiss is an individual notable enough to be recognized as a namesake of the surname Weiss, though specific widely known biographical details are not clearly established.
  • D. Kurt Back
    Kurt Back was a social psychologist known for his collaborative research in social behavior and group dynamics, including work with Leon Festinger.
  • E. Karl
    Karl is the given first name of Charles Proteus Steinmetz, the renowned German-American mathematician and electrical engineer who revolutionized the understanding of alternating current systems.
  • 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_69ca84cb580c8190a7e5f4b3bcdaf2a4 completed March 30, 2026, 2:12 p.m.
NER Named-entity recognition batch_69cd9d366c488190bc153c68fef197c2 completed April 1, 2026, 10:33 p.m.
NED1 Entity disambiguation (via context triple) batch_69d1912216d481909f6a0f977d570a93 completed April 4, 2026, 10:30 p.m.
NEDg Description generation batch_69d1926e9154819086be60bd6fa55453 completed April 4, 2026, 10:36 p.m.
NED2 Entity disambiguation (via description) batch_69d19611bbe08190b1893727c1fa05ce completed April 4, 2026, 10:52 p.m.
Created at: March 30, 2026, 8:17 p.m.