Triple

T11545687
Position Surface form Disambiguated ID Type / Status
Subject Crash Bandicoot E273770 entity
Predicate enemy P4567 FINISHED
Object Koala Kong
Koala Kong is a muscular, anthropomorphic koala who appears as a boss character in the Crash Bandicoot video game series.
 E931038 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: Koala Kong | Statement: [Crash Bandicoot, enemy, Koala Kong]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07 
Target entity: Koala Kong
Context triple: [Crash Bandicoot, enemy, Koala Kong]
  • A. Moe the Kangaroo
    Moe the Kangaroo is the costumed kangaroo mascot that represents the Virginia Military Institute at its athletic events and school functions.
  • B. The Flying Kangaroo
    The Flying Kangaroo is the iconic nickname and branding symbol of Qantas, Australia’s flag carrier airline.
  • C. Zippy the kangaroo
    Zippy the kangaroo is the costumed kangaroo mascot representing the University of Akron's athletic teams, particularly the Akron Zips football team.
  • D. Reginald the Koala
    Reginald the Koala is a fictional koala character portrayed as an operative working for the CIA’s domestic branch.
  • E. Gadzooks the Bear
    Gadzooks the Bear is a gruff but ultimately soft-hearted bear character from the Rankin/Bass stop-motion Easter special "The Easter Bunny Is Comin' to Town."
  • 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: Koala Kong
Triple: [Crash Bandicoot, enemy, Koala Kong]
Generated description
Koala Kong is a muscular, anthropomorphic koala who appears as a boss character in the Crash Bandicoot video game series.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07 
Target entity: Koala Kong
Target entity description: Koala Kong is a muscular, anthropomorphic koala who appears as a boss character in the Crash Bandicoot video game series.
  • A. Moe the Kangaroo
    Moe the Kangaroo is the costumed kangaroo mascot that represents the Virginia Military Institute at its athletic events and school functions.
  • B. The Flying Kangaroo
    The Flying Kangaroo is the iconic nickname and branding symbol of Qantas, Australia’s flag carrier airline.
  • C. Zippy the kangaroo
    Zippy the kangaroo is the costumed kangaroo mascot representing the University of Akron's athletic teams, particularly the Akron Zips football team.
  • D. Reginald the Koala
    Reginald the Koala is a fictional koala character portrayed as an operative working for the CIA’s domestic branch.
  • E. Gadzooks the Bear
    Gadzooks the Bear is a gruff but ultimately soft-hearted bear character from the Rankin/Bass stop-motion Easter special "The Easter Bunny Is Comin' to Town."
  • 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_69d6aae4dfa48190a3ab0b19a159a3c5 completed April 8, 2026, 7:22 p.m.
NER Named-entity recognition batch_69d886e3ad548190b2c88332f5d919bd completed April 10, 2026, 5:13 a.m.
NED1 Entity disambiguation (via context triple) batch_69e685de2bf88190b1f59513fd47feeb completed April 20, 2026, 8 p.m.
NEDg Description generation batch_69e68fd9d1b88190ba6057a52f51c961 completed April 20, 2026, 8:43 p.m.
NED2 Entity disambiguation (via description) batch_69e69f3de9208190b65f25c3e2d6e222 completed April 20, 2026, 9:48 p.m.
Created at: April 8, 2026, 9:37 p.m.