Triple

T1736534
Position Surface form Disambiguated ID Type / Status
Subject Harold Abrahams E37931 entity
Predicate familyName P18 FINISHED
Object Abrahams
Abrahams is a surname most notably associated with Harold Abrahams, the British Olympic sprinter portrayed in the film "Chariots of Fire."
 E195359 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: Abrahams | Statement: [Harold Abrahams, familyName, Abrahams]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07 
Target entity: Abrahams
Context triple: [Harold Abrahams, familyName, Abrahams]
  • A. Abraham
    Abraham is the given name of Abraham Lincoln, the 16th president of the United States who led the country through the Civil War and abolished slavery.
  • B. Abraham
    Abraham is a small unincorporated community located in rural Millard County in the U.S. state of Utah.
  • C. Abraham
    Abraham is a foundational patriarch in the Hebrew Bible, revered as the ancestor of the Israelites and a central figure in Jewish religious tradition.
  • D. Abram
    Abram is the middle name of James A. Garfield, the 20th president of the United States.
  • E. Avram
    Avram is the given first name of Noam Chomsky, the influential American linguist, philosopher, and political activist.
  • 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: Abrahams
Triple: [Harold Abrahams, familyName, Abrahams]
Generated description
Abrahams is a surname most notably associated with Harold Abrahams, the British Olympic sprinter portrayed in the film "Chariots of Fire."
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07 
Target entity: Abrahams
Target entity description: Abrahams is a surname most notably associated with Harold Abrahams, the British Olympic sprinter portrayed in the film "Chariots of Fire."
  • A. Abraham
    Abraham is the given name of Abraham Lincoln, the 16th president of the United States who led the country through the Civil War and abolished slavery.
  • B. Abraham
    Abraham is a small unincorporated community located in rural Millard County in the U.S. state of Utah.
  • C. Abraham
    Abraham is a foundational patriarch in the Hebrew Bible, revered as the ancestor of the Israelites and a central figure in Jewish religious tradition.
  • D. Abram
    Abram is the middle name of James A. Garfield, the 20th president of the United States.
  • E. Avram
    Avram is the given first name of Noam Chomsky, the influential American linguist, philosopher, and political activist.
  • 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_69a8861cc6ac8190ac0b2e31ccf62851 completed March 4, 2026, 7:21 p.m.
NER Named-entity recognition batch_69aa63a369048190bae352573f5082f1 completed March 6, 2026, 5:18 a.m.
NED1 Entity disambiguation (via context triple) batch_69ada0d999148190a889f761af05f431 completed March 8, 2026, 4:16 p.m.
NEDg Description generation batch_69ada207c50881909729bf565c2af9dd completed March 8, 2026, 4:21 p.m.
NED2 Entity disambiguation (via description) batch_69ada2c607fc819089d276ae9eca82a4 completed March 8, 2026, 4:24 p.m.
Created at: March 4, 2026, 7:30 p.m.