Triple

T16096372
Position Surface form Disambiguated ID Type / Status
Subject Kashyyyk E390493 entity
Predicate nativeSpecies P56480 FINISHED
Object Kashyyyk bantha
The Kashyyyk bantha is a Wookiee-world variant of the bantha species in Star Wars, adapted to the dense forests and unique ecosystems of the planet Kashyyyk.
E1193961 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: Kashyyyk bantha | Statement: [Kashyyyk, nativeSpecies, Kashyyyk bantha]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Kashyyyk bantha
Context triple: [Kashyyyk, nativeSpecies, Kashyyyk bantha]
  • A. Twi'lek
    Twi'lek are a humanoid alien species from the Star Wars universe, recognizable by their colorful skin and distinctive head-tails called lekku.
  • B. Yennadon
    Yennadon is a residential neighbourhood within the city of Maple Ridge in British Columbia, Canada.
  • C. Baiju
    Baiju is an Indian-American entrepreneur best known as the co-founder of the stock trading platform Robinhood.
  • D. Baiju
    Baiju was a 13th-century Mongol general who led Mongol forces in their campaigns into Eastern Europe.
  • E. Bantoid
    Bantoid is a major branch of the Niger-Congo language family that includes the Bantu languages and several closely related non-Bantu groups spoken primarily in Central and West Africa.
  • 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: Kashyyyk bantha
Triple: [Kashyyyk, nativeSpecies, Kashyyyk bantha]
Generated description
The Kashyyyk bantha is a Wookiee-world variant of the bantha species in Star Wars, adapted to the dense forests and unique ecosystems of the planet Kashyyyk.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07
Target entity: Kashyyyk bantha
Target entity description: The Kashyyyk bantha is a Wookiee-world variant of the bantha species in Star Wars, adapted to the dense forests and unique ecosystems of the planet Kashyyyk.
  • A. Twi'lek
    Twi'lek are a humanoid alien species from the Star Wars universe, recognizable by their colorful skin and distinctive head-tails called lekku.
  • B. Yennadon
    Yennadon is a residential neighbourhood within the city of Maple Ridge in British Columbia, Canada.
  • C. Baiju
    Baiju is an Indian-American entrepreneur best known as the co-founder of the stock trading platform Robinhood.
  • D. Baiju
    Baiju was a 13th-century Mongol general who led Mongol forces in their campaigns into Eastern Europe.
  • E. Bantoid
    Bantoid is a major branch of the Niger-Congo language family that includes the Bantu languages and several closely related non-Bantu groups spoken primarily in Central and West Africa.
  • 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_69d87f198bc48190a8b7e53ca15b7ead completed April 10, 2026, 4:39 a.m.
NER Named-entity recognition batch_69e18593d0fc8190aa3ba3edb4219aaa completed April 17, 2026, 12:57 a.m.
NED1 Entity disambiguation (via context triple) batch_69ffeb991ba88190ad568a49069f9701 completed May 10, 2026, 2:21 a.m.
NEDg Description generation batch_69ffec4898088190bed531e33418c7e5 completed May 10, 2026, 2:24 a.m.
NED2 Entity disambiguation (via description) batch_69ffecce96508190a53f100e3207ebac completed May 10, 2026, 2:26 a.m.
Created at: April 10, 2026, 4:59 a.m.