Triple

T21670121
Position Surface form Disambiguated ID Type / Status
Subject Chrysler K-cars E534822 entity
Predicate platformCode P19884 FINISHED
Object K-platform
The K-platform was Chrysler's compact, front-wheel-drive automobile architecture of the early 1980s that underpinned the influential K-car line and helped revive the company financially.
 E1495832 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: K-platform | Statement: [Chrysler K-cars, platformCode, K-platform]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07 
Target entity: K-platform
Context triple: [Chrysler K-cars, platformCode, K-platform]
  • A. KONP
    KONP is the ICAO airport code for Newport Municipal Airport in Newport, Oregon, United States.
  • B. KODA
    KODA refers to a hearing child born to one or more deaf parents, often growing up bilingual in spoken and signed languages and navigating both deaf and hearing cultures.
  • C. K4
    K4 is an alternative name for Gasherbrum II, one of the world’s fourteen 8,000-meter peaks located in the Karakoram range on the China–Pakistan border.
  • D. KIAP
    KIAP is an educational and cultural exchange initiative based in Kanpur that fosters collaboration between Indian and American institutions and communities.
  • E. KRP
    KRP is the IATA airport code for Karup Airport, a regional airport in Denmark.
  • 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: K-platform
Triple: [Chrysler K-cars, platformCode, K-platform]
Generated description
The K-platform was Chrysler's compact, front-wheel-drive automobile architecture of the early 1980s that underpinned the influential K-car line and helped revive the company financially.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07 
Target entity: K-platform
Target entity description: The K-platform was Chrysler's compact, front-wheel-drive automobile architecture of the early 1980s that underpinned the influential K-car line and helped revive the company financially.
  • A. KONP
    KONP is the ICAO airport code for Newport Municipal Airport in Newport, Oregon, United States.
  • B. KODA
    KODA refers to a hearing child born to one or more deaf parents, often growing up bilingual in spoken and signed languages and navigating both deaf and hearing cultures.
  • C. K4
    K4 is an alternative name for Gasherbrum II, one of the world’s fourteen 8,000-meter peaks located in the Karakoram range on the China–Pakistan border.
  • D. KIAP
    KIAP is an educational and cultural exchange initiative based in Kanpur that fosters collaboration between Indian and American institutions and communities.
  • E. KRP
    KRP is the IATA airport code for Karup Airport, a regional airport in Denmark.
  • 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_69e0c46898008190aa618a4af55bd1ee completed April 16, 2026, 11:13 a.m.
NER Named-entity recognition batch_69ef8a0a9b4481909477245d53f99cb0 completed April 27, 2026, 4:08 p.m.
NED1 Entity disambiguation (via context triple) batch_6a0a15a57e2081909dae14d826f0f9a9 completed May 17, 2026, 7:23 p.m.
NEDg Description generation batch_6a0a16ac5ee881909ede61c149be61fa completed May 17, 2026, 7:27 p.m.
NED2 Entity disambiguation (via description) batch_6a0a17d9a48881908d9858e40d41674c completed May 17, 2026, 7:32 p.m.
Created at: April 16, 2026, 6:37 p.m.