Triple

T16826609
Position Surface form Disambiguated ID Type / Status
Subject Ernie Harwell E409034 entity
Predicate spouse P13 FINISHED
Object Lulu Harwell
Lulu Harwell was the wife of famed baseball broadcaster Ernie Harwell and a supportive partner throughout his long career in Major League Baseball.
E1240353 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: Lulu Harwell | Statement: [Ernie Harwell, spouse, Lulu Harwell]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Lulu Harwell
Context triple: [Ernie Harwell, spouse, Lulu Harwell]
  • A. Lynesse Hightower
    Lynesse Hightower is a noblewoman from House Hightower in the world of "A Song of Ice and Fire," whose ill-fated marriage to Jorah Mormont plays a key role in his downfall and exile.
  • B. Lola Sewell
    Lola Sewell is the daughter of English actor Rufus Sewell.
  • C. Marlena Evans
    Marlena Evans is a long-running, iconic fictional psychiatrist and central heroine on the American soap opera "Days of Our Lives."
  • D. Rachel Scott
    Rachel Scott was a 17-year-old student, aspiring writer, and the first person killed in the Columbine High School shooting, later remembered for her journals and advocacy for kindness.
  • E. Hope Loring
    Hope Loring was an American screenwriter best known for co-writing the World War I aviation epic "Wings," the first film to win the Academy Award for Best Picture.
  • 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: Lulu Harwell
Triple: [Ernie Harwell, spouse, Lulu Harwell]
Generated description
Lulu Harwell was the wife of famed baseball broadcaster Ernie Harwell and a supportive partner throughout his long career in Major League Baseball.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07
Target entity: Lulu Harwell
Target entity description: Lulu Harwell was the wife of famed baseball broadcaster Ernie Harwell and a supportive partner throughout his long career in Major League Baseball.
  • A. Lynesse Hightower
    Lynesse Hightower is a noblewoman from House Hightower in the world of "A Song of Ice and Fire," whose ill-fated marriage to Jorah Mormont plays a key role in his downfall and exile.
  • B. Lola Sewell
    Lola Sewell is the daughter of English actor Rufus Sewell.
  • C. Marlena Evans
    Marlena Evans is a long-running, iconic fictional psychiatrist and central heroine on the American soap opera "Days of Our Lives."
  • D. Rachel Scott
    Rachel Scott was a 17-year-old student, aspiring writer, and the first person killed in the Columbine High School shooting, later remembered for her journals and advocacy for kindness.
  • E. Hope Loring
    Hope Loring was an American screenwriter best known for co-writing the World War I aviation epic "Wings," the first film to win the Academy Award for Best Picture.
  • 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_69d88394566c8190b3dcbdc72935f7fa completed April 10, 2026, 4:59 a.m.
NER Named-entity recognition batch_69e3b31404c88190a3b2802842ca77eb completed April 18, 2026, 4:36 p.m.
NED1 Entity disambiguation (via context triple) batch_6a00c79cdf9c8190aa20d536ca17ab81 completed May 10, 2026, 5:59 p.m.
NEDg Description generation batch_6a00ca95ebb4819091bbfe3ccc267f9a completed May 10, 2026, 6:12 p.m.
NED2 Entity disambiguation (via description) batch_6a00cb02c8bc8190a60da76bea8dabe5 completed May 10, 2026, 6:14 p.m.
Created at: April 10, 2026, 5:23 a.m.