Triple

T14837268
Position Surface form Disambiguated ID Type / Status
Subject Molten basketball E348863 entity
Predicate hasModel P2390 FINISHED
Object Molten GL7X
The Molten GL7X is a high-quality, FIBA-approved indoor basketball widely used in professional and international competitions.
E1123119 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: Molten GL7X | Statement: [Molten basketball, hasModel, Molten GL7X]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Molten GL7X
Context triple: [Molten basketball, hasModel, Molten GL7X]
  • A. XR-7
    XR-7 is a higher-end, performance-oriented trim package of the Mercury Cougar that added luxury and sporty features beyond the base model.
  • B. Mazda Gator Bowl
    The Mazda Gator Bowl was the title-sponsored name of the long-running Gator Bowl college football postseason game during the period when Mazda served as its primary corporate sponsor.
  • C. Maxus
    Maxus is a commercial vehicle brand known for producing vans, pickups, and light trucks, owned by the Chinese automotive giant SAIC Motor.
  • D. Melter
    Melter is a Marvel Comics supervillain known primarily as an enemy of Iron Man and a recurring member of villainous teams.
  • E. Mark VII Limited
    Mark VII Limited was a television and film production company founded by Jack Webb, best known for producing the police procedural series Dragnet.
  • 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: Molten GL7X
Triple: [Molten basketball, hasModel, Molten GL7X]
Generated description
The Molten GL7X is a high-quality, FIBA-approved indoor basketball widely used in professional and international competitions.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07
Target entity: Molten GL7X
Target entity description: The Molten GL7X is a high-quality, FIBA-approved indoor basketball widely used in professional and international competitions.
  • A. XR-7
    XR-7 is a higher-end, performance-oriented trim package of the Mercury Cougar that added luxury and sporty features beyond the base model.
  • B. Mazda Gator Bowl
    The Mazda Gator Bowl was the title-sponsored name of the long-running Gator Bowl college football postseason game during the period when Mazda served as its primary corporate sponsor.
  • C. Maxus
    Maxus is a commercial vehicle brand known for producing vans, pickups, and light trucks, owned by the Chinese automotive giant SAIC Motor.
  • D. Melter
    Melter is a Marvel Comics supervillain known primarily as an enemy of Iron Man and a recurring member of villainous teams.
  • E. Mark VII Limited
    Mark VII Limited was a television and film production company founded by Jack Webb, best known for producing the police procedural series Dragnet.
  • 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_69d822ec69008190a9232caa68836872 completed April 9, 2026, 10:06 p.m.
NER Named-entity recognition batch_69ded28d0ddc8190a34e3e2d469ab762 completed April 14, 2026, 11:49 p.m.
NED1 Entity disambiguation (via context triple) batch_69fe64fc8cdc8190a142a2a3ef889e72 completed May 8, 2026, 10:34 p.m.
NEDg Description generation batch_69fe65e5a29c819099b981499a4f4bc8 completed May 8, 2026, 10:38 p.m.
NED2 Entity disambiguation (via description) batch_69fe66687bc88190a05acf107c0a1388 completed May 8, 2026, 10:40 p.m.
Created at: April 10, 2026, 1:52 a.m.