Triple

T14779011
Position Surface form Disambiguated ID Type / Status
Subject Perdita E347340 entity
Predicate hasChildren P289 FINISHED
Object Lucky
Lucky is one of the Dalmatian puppies from Disney’s "101 Dalmatians," known for being the runt of the litter who nearly dies at birth but is revived and cherished by his owners.
 E1082610 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: Lucky | Statement: [Perdita, hasChildren, Lucky]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07 
Target entity: Lucky
Context triple: [Perdita, hasChildren, Lucky]
  • A. Lucky
    "Lucky" is a popular Afrobeats/hip-hop song by Ghanaian rapper Sarkodie, known for its smooth blend of rap and melodic vocals.
  • B. Lucky
    Lucky is the nickname of John "Lucky" Garnett, likely highlighting a reputation for good fortune or narrow escapes.
  • C. Lucky
    "Lucky" is a popular duet by American singers Colbie Caillat and Jason Mraz, known for its mellow acoustic pop style and romantic lyrics.
  • D. Lucky
    Lucky is a tormented, subservient figure in Samuel Beckett’s play "Waiting for Godot," known for his near-muteness and one explosive, chaotic monologue that reflects the play’s themes of absurdity and existential despair.
  • E. Lucky
    Lucky is a bestselling novel by Jackie Collins that follows the glamorous, ruthless world of Lucky Santangelo in the high-stakes realms of power, sex, and crime.
  • 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: Lucky
Triple: [Perdita, hasChildren, Lucky]
Generated description
Lucky is one of the Dalmatian puppies from Disney’s "101 Dalmatians," known for being the runt of the litter who nearly dies at birth but is revived and cherished by his owners.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07 
Target entity: Lucky
Target entity description: Lucky is one of the Dalmatian puppies from Disney’s "101 Dalmatians," known for being the runt of the litter who nearly dies at birth but is revived and cherished by his owners.
  • A. Lucky chosen
    Lucky is one of the most recognizable Dalmatian puppies in Disney's "101 Dalmatians," known for his distinctive spots and plucky, TV-obsessed personality.
  • B. Lucky
    Lucky is a recurring dog character in the animated children's series "Bluey," known as Bluey's sporty next-door neighbor and friend.
  • C. Lucky
    Lucky is the protagonist of the 1993 film "Poetic Justice," portrayed by Tupac Shakur as a sensitive and complex mail carrier navigating love, grief, and self-discovery.
  • D. Lucky
    Lucky is the nickname of John "Lucky" Garnett, likely highlighting a reputation for good fortune or narrow escapes.
  • E. Lucky
    Lucky is a character in the crime drama film "Waist Deep," involved in the gritty, high-stakes world surrounding the protagonist.
  • 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_69d822e9b9e08190bedcc31a163fda82 completed April 9, 2026, 10:06 p.m.
NER Named-entity recognition batch_69deca9c7cac8190ba900df95e42e318 completed April 14, 2026, 11:15 p.m.
NED1 Entity disambiguation (via context triple) batch_69fe0d00d46c8190b6289a9b8511a8fb completed May 8, 2026, 4:19 p.m.
NEDg Description generation batch_69fe17e255408190b1155c06854715ea completed May 8, 2026, 5:05 p.m.
NED2 Entity disambiguation (via description) batch_69fe1865a1d8819085d62375ab6cccfe completed May 8, 2026, 5:07 p.m.
Created at: April 10, 2026, 1:31 a.m.