Triple

T3790084
Position Surface form Disambiguated ID Type / Status
Subject Eddie Marsan E89622 entity
Predicate twitterUsername P2943 FINISHED
Object eddiemarsan
Eddie Marsan is a British character actor known for his versatile roles in films and television series such as "Ray Donovan," "Happy-Go-Lucky," and "Sherlock Holmes."
 E388467 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: eddiemarsan | Statement: [Eddie Marsan, twitterUsername, eddiemarsan]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07 
Target entity: eddiemarsan
Context triple: [Eddie Marsan, twitterUsername, eddiemarsan]
  • A. EDDI
    EDDI is the ICAO airport code for Berlin Tempelhof Airport, the historic inner-city airfield in Berlin, Germany.
  • B. EMMI
    EMMI is a multi-mode optical instrument used for imaging and spectroscopy on the NTT 3.58 m Telescope at the La Silla Observatory.
  • C. Eddy
    Eddy is the married surname of Mary Baker Eddy, the American religious leader who founded Christian Science.
  • D. Marsden
    Marsden is a village in West Yorkshire, England, situated in the Colne Valley near the Pennines and known for its industrial heritage and scenic moorland surroundings.
  • E. E-n-i-d
    E-n-i-d is an alternative hyphenated spelling of the given name "Enid," which is of Welsh origin and often associated with literary and historical usage.
  • 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: eddiemarsan
Triple: [Eddie Marsan, twitterUsername, eddiemarsan]
Generated description
Eddie Marsan is a British character actor known for his versatile roles in films and television series such as "Ray Donovan," "Happy-Go-Lucky," and "Sherlock Holmes."
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07 
Target entity: eddiemarsan
Target entity description: Eddie Marsan is a British character actor known for his versatile roles in films and television series such as "Ray Donovan," "Happy-Go-Lucky," and "Sherlock Holmes."
  • A. EDDI
    EDDI is the ICAO airport code for Berlin Tempelhof Airport, the historic inner-city airfield in Berlin, Germany.
  • B. EMMI
    EMMI is a multi-mode optical instrument used for imaging and spectroscopy on the NTT 3.58 m Telescope at the La Silla Observatory.
  • C. Eddy
    Eddy is the married surname of Mary Baker Eddy, the American religious leader who founded Christian Science.
  • D. Marsden
    Marsden is a village in West Yorkshire, England, situated in the Colne Valley near the Pennines and known for its industrial heritage and scenic moorland surroundings.
  • E. E-n-i-d
    E-n-i-d is an alternative hyphenated spelling of the given name "Enid," which is of Welsh origin and often associated with literary and historical usage.
  • 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_69aed9597d6881909b6ee3b9de859223 completed March 9, 2026, 2:29 p.m.
NER Named-entity recognition batch_69aee76733248190a24a1143c64bd6c6 completed March 9, 2026, 3:29 p.m.
NED1 Entity disambiguation (via context triple) batch_69b4f05326dc81909a4523c8f2062c25 completed March 14, 2026, 5:21 a.m.
NEDg Description generation batch_69b4f173d66881909301bfc45d10b3d1 completed March 14, 2026, 5:26 a.m.
NED2 Entity disambiguation (via description) batch_69b4f1ecdd788190aebea36578923fad completed March 14, 2026, 5:28 a.m.
Created at: March 9, 2026, 3:15 p.m.