Triple

T10601658
Position Surface form Disambiguated ID Type / Status
Subject Alfred Roome E275762 entity
Predicate familyName P18 FINISHED
Object Roome
Roome is a surname most notably associated with Alfred Roome, a British film editor and director.
E874081 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: Roome | Statement: [Alfred Roome, familyName, Roome]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Roome
Context triple: [Alfred Roome, familyName, Roome]
  • A. Romm
    Romm is a surname most notably associated with Soviet film director and screenwriter Mikhail Romm.
  • B. Rommen
    Rommen is a neighborhood in Oslo, Norway, situated within the Søndre Nordstrand borough.
  • C. Rometty
    Rometty is the surname of Ginni Rometty, the former chairman, president, and CEO of IBM.
  • D. Sitra
    Sitra is a small island in Bahrain known for its residential communities, industrial facilities, and role in the country’s oil and gas infrastructure.
  • E. Travilla
    Travilla was an American costume designer best known for creating some of Marilyn Monroe’s most iconic film dresses, including those in "Gentlemen Prefer Blondes."
  • 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: Roome
Triple: [Alfred Roome, familyName, Roome]
Generated description
Roome is a surname most notably associated with Alfred Roome, a British film editor and director.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07
Target entity: Roome
Target entity description: Roome is a surname most notably associated with Alfred Roome, a British film editor and director.
  • A. Romm
    Romm is a surname most notably associated with Soviet film director and screenwriter Mikhail Romm.
  • B. Rommen
    Rommen is a neighborhood in Oslo, Norway, situated within the Søndre Nordstrand borough.
  • C. Rometty
    Rometty is the surname of Ginni Rometty, the former chairman, president, and CEO of IBM.
  • D. Sitra
    Sitra is a small island in Bahrain known for its residential communities, industrial facilities, and role in the country’s oil and gas infrastructure.
  • E. Travilla
    Travilla was an American costume designer best known for creating some of Marilyn Monroe’s most iconic film dresses, including those in "Gentlemen Prefer Blondes."
  • 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_69d6aaf948d88190806cc3a8c47a3fb2 completed April 8, 2026, 7:22 p.m.
NER Named-entity recognition batch_69d6ded61d5c8190b13890c964b59949 completed April 8, 2026, 11:03 p.m.
NED1 Entity disambiguation (via context triple) batch_69d95ea8f1688190aa36e29b52667d26 completed April 10, 2026, 8:33 p.m.
NEDg Description generation batch_69d95f81955c8190b629d57a034a4b76 completed April 10, 2026, 8:37 p.m.
NED2 Entity disambiguation (via description) batch_69d961047a78819088094e02c0b99f60 completed April 10, 2026, 8:43 p.m.
Created at: April 8, 2026, 7:31 p.m.