Triple

T296087
Position Surface form Disambiguated ID Type / Status
Subject Idris Elba E6094 entity
Predicate characterRole P268 FINISHED
Object Heimdall
Heimdall is a powerful Asgardian guardian in the Marvel universe, known for his all-seeing vision, immense strength, and duty to watch over the Bifröst Bridge.
E38399 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: Heimdall | Statement: [Idris Elba, characterRole, Heimdall]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Heimdall
Context triple: [Idris Elba, characterRole, Heimdall]
  • A. Gunnar
    Gunnar is a masculine given name of Old Norse origin, commonly used in Scandinavian countries and associated with warriors or bold fighters.
  • B. Audun Tron
    Audun Tron is a Norwegian politician who served as the mayor of Lillehammer during the period when the city hosted the 1994 Winter Olympics.
  • C. Thersander
    Thersander is a figure in Greek mythology, known as a descendant of the royal house of Thebes and one of the Epigoni who attacked the city.
  • D. Hanna Lejonqvist
    Hanna Lejonqvist is a film editor known for her work on the documentary "I Am Greta," which follows climate activist Greta Thunberg.
  • E. Johanus
    Johanus is a given name, likely a variant or diminutive of Johan, used as a personal first name in some cultures.
  • 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: Heimdall
Triple: [Idris Elba, characterRole, Heimdall]
Generated description
Heimdall is a powerful Asgardian guardian in the Marvel universe, known for his all-seeing vision, immense strength, and duty to watch over the Bifröst Bridge.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07
Target entity: Heimdall
Target entity description: Heimdall is a powerful Asgardian guardian in the Marvel universe, known for his all-seeing vision, immense strength, and duty to watch over the Bifröst Bridge.
  • A. Gunnar
    Gunnar is a masculine given name of Old Norse origin, commonly used in Scandinavian countries and associated with warriors or bold fighters.
  • B. Audun Tron
    Audun Tron is a Norwegian politician who served as the mayor of Lillehammer during the period when the city hosted the 1994 Winter Olympics.
  • C. Thersander
    Thersander is a figure in Greek mythology, known as a descendant of the royal house of Thebes and one of the Epigoni who attacked the city.
  • D. Hanna Lejonqvist
    Hanna Lejonqvist is a film editor known for her work on the documentary "I Am Greta," which follows climate activist Greta Thunberg.
  • E. Johanus
    Johanus is a given name, likely a variant or diminutive of Johan, used as a personal first name in some cultures.
  • 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_69a2e79114b081909490b3bf5a5dbb51 completed Feb. 28, 2026, 1:03 p.m.
NER Named-entity recognition batch_69a2e979663481908cf9622e59fed041 completed Feb. 28, 2026, 1:11 p.m.
NED1 Entity disambiguation (via context triple) batch_69a3a88778b48190856af2e89d21621a completed March 1, 2026, 2:46 a.m.
NEDg Description generation batch_69a3a8f94d848190ad2410b5f8f8f79d completed March 1, 2026, 2:48 a.m.
NED2 Entity disambiguation (via description) batch_69a3a96d153081909fab6bace45206ec completed March 1, 2026, 2:50 a.m.
Created at: Feb. 28, 2026, 1:06 p.m.