Triple

T3342847
Position Surface form Disambiguated ID Type / Status
Subject CSI: NY E70297 entity
Predicate portrayedBy P1507 FINISHED
Object Anna Belknap
Anna Belknap is an American actress best known for playing Detective Lindsay Monroe on the television series CSI: NY.
E350888 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: Anna Belknap | Statement: [CSI: NY, portrayedBy, Anna Belknap]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Anna Belknap
Context triple: [CSI: NY, portrayedBy, Anna Belknap]
  • A. Louise B. Cromwell
    Louise B. Cromwell was an American socialite and heiress best known as the first wife of General Douglas MacArthur.
  • B. Sheila Ford Hamp
    Sheila Ford Hamp is an American businesswoman and member of the Ford family who serves as principal owner and chair of the NFL’s Detroit Lions.
  • C. Katherine Woodcock
    Katherine Woodcock was the second wife of the English poet John Milton, remembered primarily through his sonnet mourning her death shortly after childbirth.
  • D. Mary Harrison McKee
    Mary Harrison McKee was the daughter of U.S. President Benjamin Harrison who served as White House hostess and de facto First Lady during part of his administration.
  • E. Mary Yates
    Mary Yates is best known as the wife of prominent American journalist and longtime 60 Minutes correspondent Mike Wallace.
  • 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: Anna Belknap
Triple: [CSI: NY, portrayedBy, Anna Belknap]
Generated description
Anna Belknap is an American actress best known for playing Detective Lindsay Monroe on the television series CSI: NY.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07
Target entity: Anna Belknap
Target entity description: Anna Belknap is an American actress best known for playing Detective Lindsay Monroe on the television series CSI: NY.
  • A. Louise B. Cromwell
    Louise B. Cromwell was an American socialite and heiress best known as the first wife of General Douglas MacArthur.
  • B. Sheila Ford Hamp
    Sheila Ford Hamp is an American businesswoman and member of the Ford family who serves as principal owner and chair of the NFL’s Detroit Lions.
  • C. Katherine Woodcock
    Katherine Woodcock was the second wife of the English poet John Milton, remembered primarily through his sonnet mourning her death shortly after childbirth.
  • D. Mary Harrison McKee
    Mary Harrison McKee was the daughter of U.S. President Benjamin Harrison who served as White House hostess and de facto First Lady during part of his administration.
  • E. Mary Yates
    Mary Yates is best known as the wife of prominent American journalist and longtime 60 Minutes correspondent Mike Wallace.
  • 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_69ad85a405e48190b6e68de7cf9f319e completed March 8, 2026, 2:20 p.m.
NER Named-entity recognition batch_69adb1f06f8c8190a6b7c56ac3f5ff07 completed March 8, 2026, 5:29 p.m.
NED1 Entity disambiguation (via context triple) batch_69b3251d49d08190b74483b69024acff completed March 12, 2026, 8:42 p.m.
NEDg Description generation batch_69b326a29cbc8190a5ae5fd5851ed0c7 completed March 12, 2026, 8:48 p.m.
NED2 Entity disambiguation (via description) batch_69b3270962648190925b04e44542c9c9 completed March 12, 2026, 8:50 p.m.
Created at: March 8, 2026, 3:12 p.m.