Triple

T16441545
Position Surface form Disambiguated ID Type / Status
Subject Melrose Place E399312 entity
Predicate portrayedBy P1507 FINISHED
Object Laura Leighton
Laura Leighton is an American actress best known for her role as the scheming Sydney Andrews on the 1990s primetime soap opera "Melrose Place."
E1219516 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: Laura Leighton | Statement: [Melrose Place, portrayedBy, Laura Leighton]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Laura Leighton
Context triple: [Melrose Place, portrayedBy, Laura Leighton]
  • A. Laura Davenport
    Laura Davenport is the daughter of English actor Nigel Davenport.
  • B. Leah Haywood
    Leah Haywood is an Australian singer-songwriter and producer known for both her own pop releases and her songwriting work for major international artists.
  • C. Laura Dalton
    Laura Dalton is the central protagonist of the British sitcom "A Fine Romance," around whose romantic and personal life the series revolves.
  • D. Emily Woodruff
    Emily Woodruff was the wife of Canadian-American actor Hume Cronyn and is primarily known for her connection to his life and career.
  • E. Laura Harrington
    Laura Harrington is an American actress best known for her role in the 1986 Stephen King film "Maximum Overdrive."
  • 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: Laura Leighton
Triple: [Melrose Place, portrayedBy, Laura Leighton]
Generated description
Laura Leighton is an American actress best known for her role as the scheming Sydney Andrews on the 1990s primetime soap opera "Melrose Place."
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07
Target entity: Laura Leighton
Target entity description: Laura Leighton is an American actress best known for her role as the scheming Sydney Andrews on the 1990s primetime soap opera "Melrose Place."
  • A. Laura Davenport
    Laura Davenport is the daughter of English actor Nigel Davenport.
  • B. Leah Haywood
    Leah Haywood is an Australian singer-songwriter and producer known for both her own pop releases and her songwriting work for major international artists.
  • C. Laura Dalton
    Laura Dalton is the central protagonist of the British sitcom "A Fine Romance," around whose romantic and personal life the series revolves.
  • D. Emily Woodruff
    Emily Woodruff was the wife of Canadian-American actor Hume Cronyn and is primarily known for her connection to his life and career.
  • E. Laura Harrington
    Laura Harrington is an American actress best known for her role in the 1986 Stephen King film "Maximum Overdrive."
  • 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_69d87f2c6778819080fcfae53be8f12a completed April 10, 2026, 4:40 a.m.
NER Named-entity recognition batch_69e32ba91dc48190bc35db60f63d36d3 completed April 18, 2026, 6:58 a.m.
NED1 Entity disambiguation (via context triple) batch_6a00679d15b08190b4e70e4337bff88d completed May 10, 2026, 11:10 a.m.
NEDg Description generation batch_6a0068a384e0819093c174a46ea5ce10 completed May 10, 2026, 11:14 a.m.
NED2 Entity disambiguation (via description) batch_6a0068fa85448190aef06ff27fe16305 completed May 10, 2026, 11:16 a.m.
Created at: April 10, 2026, 5:10 a.m.