Triple

T389869
Position Surface form Disambiguated ID Type / Status
Subject Lucille Ball E8857 entity
Predicate familyName P18 FINISHED
Object Ball
Ball is a common English surname borne by numerous individuals, including the famed American comedian and actress Lucille Ball.
E49180 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: Ball | Statement: [Lucille Ball, familyName, Ball]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Ball
Context triple: [Lucille Ball, familyName, Ball]
  • A. The Ball
    The Ball is the popular nickname for Reunion Tower, a distinctive geodesic observation tower and Dallas landmark known for its glowing spherical top.
  • B. Q-balls
    Q-balls are hypothetical, stable, non-topological solitons predicted in certain quantum field theories, often considered as exotic candidates for dark matter or new physics beyond the Standard Model.
  • C. Bronze Ball
    The Bronze Ball is the FIFA Club World Cup’s third-place individual award given to one of the tournament’s best-performing players.
  • D. Ballomar
    Ballomar was a 2nd-century chieftain of the Marcomanni who led major Germanic incursions into the Roman Empire during the Marcomannic Wars.
  • E. Horseshoe
    Horseshoe is a well-known casino and racetrack brand in the United States, recognized for its gambling, entertainment, and hospitality offerings.
  • 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: Ball
Triple: [Lucille Ball, familyName, Ball]
Generated description
Ball is a common English surname borne by numerous individuals, including the famed American comedian and actress Lucille Ball.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07
Target entity: Ball
Target entity description: Ball is a common English surname borne by numerous individuals, including the famed American comedian and actress Lucille Ball.
  • A. The Ball
    The Ball is the popular nickname for Reunion Tower, a distinctive geodesic observation tower and Dallas landmark known for its glowing spherical top.
  • B. Q-balls
    Q-balls are hypothetical, stable, non-topological solitons predicted in certain quantum field theories, often considered as exotic candidates for dark matter or new physics beyond the Standard Model.
  • C. Bronze Ball
    The Bronze Ball is the FIFA Club World Cup’s third-place individual award given to one of the tournament’s best-performing players.
  • D. Ballomar
    Ballomar was a 2nd-century chieftain of the Marcomanni who led major Germanic incursions into the Roman Empire during the Marcomannic Wars.
  • E. Horseshoe
    Horseshoe is a well-known casino and racetrack brand in the United States, recognized for its gambling, entertainment, and hospitality offerings.
  • 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_69a2e7f55c60819097aff65ea2ca2832 completed Feb. 28, 2026, 1:04 p.m.
NER Named-entity recognition batch_69a2ec5bdc848190826701590070497b completed Feb. 28, 2026, 1:23 p.m.
NED1 Entity disambiguation (via context triple) batch_69a4035310608190a1e0f807cb93e1e1 completed March 1, 2026, 9:13 a.m.
NEDg Description generation batch_69a403a7c1488190a7773a5ae8a8cec7 completed March 1, 2026, 9:15 a.m.
NED2 Entity disambiguation (via description) batch_69a40428b014819091c6534ba35a11ff completed March 1, 2026, 9:17 a.m.
Created at: Feb. 28, 2026, 1:08 p.m.