Triple

T22881548
Position Surface form Disambiguated ID Type / Status
Subject Madeleine L’Engle E567485 entity
Predicate spouse P13 FINISHED
Object Hugh Franklin
Hugh Franklin was an American stage and television actor best known for his long-running role on the soap opera "All My Children."
E1559040 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: Hugh Franklin | Statement: [Madeleine L’Engle, spouse, Hugh Franklin]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Hugh Franklin
Context triple: [Madeleine L’Engle, spouse, Hugh Franklin]
  • A. Hugh Franklin
    Hugh Franklin was a British suffragist and political activist known for his militant campaigning for women's voting rights in the early 20th century.
  • B. Morris Franklin
    Morris Franklin was a 19th-century American lawyer and businessman best known for co-founding the Metropolitan Life Insurance Company.
  • C. Howard Franklin
    Howard Franklin is an American screenwriter and film director known for his work on movies such as "Quick Change" and "The Name of the Rose."
  • D. Frank Lippencott
    Frank Lippencott is a fictional character best known as one of Eileen Sherwood’s suitors in the musical and film "Wonderful Town."
  • E. Franklin Dow
    Franklin Dow is a cinematographer best known for his work on the acclaimed 2014 documentary film "Virunga."
  • 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: Hugh Franklin
Triple: [Madeleine L’Engle, spouse, Hugh Franklin]
Generated description
Hugh Franklin was an American stage and television actor best known for his long-running role on the soap opera "All My Children."
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07
Target entity: Hugh Franklin
Target entity description: Hugh Franklin was an American stage and television actor best known for his long-running role on the soap opera "All My Children."
  • A. Hugh Franklin
    Hugh Franklin was a British suffragist and political activist known for his militant campaigning for women's voting rights in the early 20th century.
  • B. Morris Franklin
    Morris Franklin was a 19th-century American lawyer and businessman best known for co-founding the Metropolitan Life Insurance Company.
  • C. Howard Franklin
    Howard Franklin is an American screenwriter and film director known for his work on movies such as "Quick Change" and "The Name of the Rose."
  • D. Frank Lippencott
    Frank Lippencott is a fictional character best known as one of Eileen Sherwood’s suitors in the musical and film "Wonderful Town."
  • E. Franklin Dow
    Franklin Dow is a cinematographer best known for his work on the acclaimed 2014 documentary film "Virunga."
  • 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_69e2458a92ec81908fc1cd5f6407d2ab completed April 17, 2026, 2:36 p.m.
NER Named-entity recognition batch_69f17f5cd98c8190b3c31ffd4c066331 completed April 29, 2026, 3:47 a.m.
NED1 Entity disambiguation (via context triple) batch_6a0bae9e1a24819087d826cf677fcad5 completed May 19, 2026, 12:28 a.m.
NEDg Description generation batch_6a0bb08f167081908ff4bd13e291afb5 completed May 19, 2026, 12:36 a.m.
NED2 Entity disambiguation (via description) batch_6a0bb10db81c8190a23d57c422a71675 completed May 19, 2026, 12:38 a.m.
Created at: April 17, 2026, 3:39 p.m.