Triple

T17245256
Position Surface form Disambiguated ID Type / Status
Subject Kurt Ingston E418606 entity
Predicate hasRelative P367 FINISHED
Object Margaret Ingston
Margaret Ingston is a fictional character associated with Kurt Ingston, likely appearing as a family member in the 1940s horror film "Night Monster."
E1460259 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: Margaret Ingston | Statement: [Kurt Ingston, hasRelative, Margaret Ingston]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Margaret Ingston
Context triple: [Kurt Ingston, hasRelative, Margaret Ingston]
  • A. Margaret Boals
    Margaret Boals is the daughter of acclaimed American character actress Margo Martindale.
  • B. Margaret McNair Stokes
    Margaret McNair Stokes was a 19th-century Irish antiquarian, illustrator, and writer known for her influential work on early Christian art and Irish archaeology.
  • C. Margaret Williams
    Margaret Williams is a fictional character from the classic American television sitcom "Make Room for Daddy" (also known as "The Danny Thomas Show").
  • D. Margaret Sims
    Margaret Sims was the woman who served as the ceremonial sponsor for the U.S. Navy destroyer USS Sims (DD-409), after whom the ship was named.
  • E. Marjorie Fowler
    Marjorie Fowler was an American film editor known for her work on numerous Hollywood productions from the 1950s through the 1970s.
  • 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: Margaret Ingston
Triple: [Kurt Ingston, hasRelative, Margaret Ingston]
Generated description
Margaret Ingston is a fictional character associated with Kurt Ingston, likely appearing as a family member in the 1940s horror film "Night Monster."
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07
Target entity: Margaret Ingston
Target entity description: Margaret Ingston is a fictional character associated with Kurt Ingston, likely appearing as a family member in the 1940s horror film "Night Monster."
  • A. Margaret Boals
    Margaret Boals is the daughter of acclaimed American character actress Margo Martindale.
  • B. Margaret McNair Stokes
    Margaret McNair Stokes was a 19th-century Irish antiquarian, illustrator, and writer known for her influential work on early Christian art and Irish archaeology.
  • C. Margaret Williams
    Margaret Williams is a fictional character from the classic American television sitcom "Make Room for Daddy" (also known as "The Danny Thomas Show").
  • D. Margaret Sims
    Margaret Sims was the woman who served as the ceremonial sponsor for the U.S. Navy destroyer USS Sims (DD-409), after whom the ship was named.
  • E. Marjorie Fowler
    Marjorie Fowler was an American film editor known for her work on numerous Hollywood productions from the 1950s through the 1970s.
  • 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_69d886d8e96081909870bff6c3d0bf09 completed April 10, 2026, 5:12 a.m.
NER Named-entity recognition batch_69e42e22fb2c8190aea5d3872095bf46 completed April 19, 2026, 1:21 a.m.
NED1 Entity disambiguation (via context triple) batch_6a092f9b9cfc819083537d00a635b8e5 completed May 17, 2026, 3:01 a.m.
NEDg Description generation batch_6a0930e11bd08190802e33af979ed5b4 completed May 17, 2026, 3:07 a.m.
NED2 Entity disambiguation (via description) batch_6a09316371e08190af8cb6c05b21f433 completed May 17, 2026, 3:09 a.m.
Created at: April 10, 2026, 5:39 a.m.