Triple

T8038749
Position Surface form Disambiguated ID Type / Status
Subject Metricom E187380 entity
Predicate product P490 FINISHED
Object Ricochet
Ricochet was an early wireless internet service network developed by Metricom that provided mobile, high-speed data access in urban areas before Wi-Fi and modern cellular data became widespread.
 E706626 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: Ricochet | Statement: [Metricom, product, Ricochet]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07 
Target entity: Ricochet
Context triple: [Metricom, product, Ricochet]
  • A. Ricochet
    Ricochet is a 1991 action thriller film in which John Lithgow plays a sadistic criminal seeking revenge on a cop who put him behind bars.
  • B. Ricochet
    Ricochet is a wild mouse–style steel roller coaster known for its sharp turns and sudden drops at the Carowinds amusement park.
  • C. Bounce
    "Bounce" is a popular Afrobeats song by Nigerian singer Rema, known for its energetic production and catchy, dance-oriented style.
  • D. Bounce
    "Bounce" is a 2002 hard rock album by Bon Jovi that reflects themes of resilience and renewal, influenced in part by the aftermath of the September 11 attacks.
  • E. The Kick
    "The Kick" is a popular Afrobeats track by Nigerian singer Wande Coal, known for its catchy rhythm and dance-floor appeal.
  • 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: Ricochet
Triple: [Metricom, product, Ricochet]
Generated description
Ricochet was an early wireless internet service network developed by Metricom that provided mobile, high-speed data access in urban areas before Wi-Fi and modern cellular data became widespread.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07 
Target entity: Ricochet
Target entity description: Ricochet was an early wireless internet service network developed by Metricom that provided mobile, high-speed data access in urban areas before Wi-Fi and modern cellular data became widespread.
  • A. Ricochet
    Ricochet is a 1991 action thriller film in which John Lithgow plays a sadistic criminal seeking revenge on a cop who put him behind bars.
  • B. Ricochet
    Ricochet is a wild mouse–style steel roller coaster known for its sharp turns and sudden drops at the Carowinds amusement park.
  • C. Bounce
    "Bounce" is a popular Afrobeats song by Nigerian singer Rema, known for its energetic production and catchy, dance-oriented style.
  • D. Bounce
    "Bounce" is a 2002 hard rock album by Bon Jovi that reflects themes of resilience and renewal, influenced in part by the aftermath of the September 11 attacks.
  • E. The Kick
    "The Kick" is a popular Afrobeats track by Nigerian singer Wande Coal, known for its catchy rhythm and dance-floor appeal.
  • 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_69ca82b00cb48190b59a300f70e97bd7 completed March 30, 2026, 2:03 p.m.
NER Named-entity recognition batch_69cb3f19a6b4819085e2887fb0c54d08 completed March 31, 2026, 3:27 a.m.
NED1 Entity disambiguation (via context triple) batch_69cc570090a48190b84ba8325563148e completed March 31, 2026, 11:21 p.m.
NEDg Description generation batch_69cc58edb31881909b6efd2fbbc2480e completed March 31, 2026, 11:29 p.m.
NED2 Entity disambiguation (via description) batch_69cc5cc9161c8190aae90f453f6d98c0 completed March 31, 2026, 11:46 p.m.
Created at: March 30, 2026, 5:23 p.m.