Triple

T10464454
Position Surface form Disambiguated ID Type / Status
Subject Harry Elkins Widener E246755 entity
Predicate givenName P17 FINISHED
Object Harry
Harry is the given name of Harry Elkins Widener, an American book collector and bibliophile who died in the sinking of the Titanic and for whom Harvard's Widener Library is named.
 E246755 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: Harry | Statement: [Harry Elkins Widener, givenName, Harry]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07 
Target entity: Harry
Context triple: [Harry Elkins Widener, givenName, Harry]
  • A. Harry
    Harry is the given name of Harry Augustus Garfield, an American lawyer, academic, and public official who served as the first head of the U.S. Fuel Administration during World War I.
  • B. Harry
    Harry is the given name of Harry F. Byrd Sr., a prominent 20th-century American politician and long-serving U.S. Senator from Virginia.
  • C. Harry
    Harry is the given first name of American basketball player and coach Buddy Jeannette.
  • D. Harry
    Harry is the given first name of legendary American and Canadian football coach Bud Grant, who led the Minnesota Vikings to multiple Super Bowl appearances.
  • E. Harry
    Harry is the given name of Lord Woolf, a prominent British judge and former Lord Chief Justice of England and Wales.
  • 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: Harry
Triple: [Harry Elkins Widener, givenName, Harry]
Generated description
Harry is the given name of Harry Elkins Widener, an American book collector and bibliophile who died in the sinking of the Titanic and for whom Harvard's Widener Library is named.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07 
Target entity: Harry
Target entity description: Harry is the given name of Harry Elkins Widener, an American book collector and bibliophile who died in the sinking of the Titanic and for whom Harvard's Widener Library is named.
  • A. Harry chosen
    Harry is the given name of Harry Elkins Widener, an American book collector and Harvard University benefactor who died in the sinking of the Titanic.
  • B. Harry
    Harry is the given name of Harry M. Wegeforth, an American physician and founder of the San Diego Zoo.
  • C. Harry
    Harry is the given name of Harry Nyquist, a pioneering engineer and physicist known for foundational contributions to information theory and telecommunications.
  • D. Harry
    Harry is the given name of Harry Nilsson, the influential American singer-songwriter known for hits like "Without You" and "Everybody's Talkin'."
  • E. Harry
    Harry is the given name of Harry Emerson Fosdick, a prominent early 20th-century American pastor and liberal Protestant theologian.
  • F. None of above.

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_69d381c16c248190a2fe5b471e584e9c completed April 6, 2026, 9:49 a.m.
NER Named-entity recognition batch_69d50886c2a8819086da6c08356ec6bf completed April 7, 2026, 1:37 p.m.
NED1 Entity disambiguation (via context triple) batch_69d89fd865688190b0b5708481f397f4 completed April 10, 2026, 6:59 a.m.
NEDg Description generation batch_69d8a43ae8a48190b1c05b6a91dfed9a completed April 10, 2026, 7:18 a.m.
NED2 Entity disambiguation (via description) batch_69d8b8fe1b9c8190b5a4787797ad7120 completed April 10, 2026, 8:46 a.m.
Created at: April 6, 2026, 12:19 p.m.