Triple

T17537404
Position Surface form Disambiguated ID Type / Status
Subject Tensor G3 E427096 entity
Predicate successor P78 FINISHED
Object Tensor G4
Tensor G4 is a next-generation Google-designed mobile system-on-chip that powers Pixel devices with improved AI, performance, and efficiency over its predecessor.
 E1274024 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: Tensor G4 | Statement: [Tensor G3, successor, Tensor G4]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07 
Target entity: Tensor G4
Context triple: [Tensor G3, successor, Tensor G4]
  • A. G4
    G4 is the IATA airline designator assigned to Allegiant Air, a U.S.-based low-cost carrier.
  • B. G4
    G4 is a family of PowerPC microprocessors developed by Motorola and used in various Apple Macintosh computers in the late 1990s and early 2000s.
  • C. G4
    G4 is the route designation for the major Beijing–Hong Kong–Macau Expressway, a key north–south artery in China’s national expressway network.
  • D. Tensor G3 chip
    The Tensor G3 chip is Google's custom third-generation mobile processor designed to power Pixel devices with advanced AI, machine learning, and efficiency-focused performance.
  • E. GTC
    GTC is a Polish vehicle registration code assigned to a specific county within the Pomeranian Voivodeship.
  • 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: Tensor G4
Triple: [Tensor G3, successor, Tensor G4]
Generated description
Tensor G4 is a next-generation Google-designed mobile system-on-chip that powers Pixel devices with improved AI, performance, and efficiency over its predecessor.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07 
Target entity: Tensor G4
Target entity description: Tensor G4 is a next-generation Google-designed mobile system-on-chip that powers Pixel devices with improved AI, performance, and efficiency over its predecessor.
  • A. G4
    G4 is the IATA airline designator assigned to Allegiant Air, a U.S.-based low-cost carrier.
  • B. G4
    G4 is a family of PowerPC microprocessors developed by Motorola and used in various Apple Macintosh computers in the late 1990s and early 2000s.
  • C. G4
    G4 is the route designation for the major Beijing–Hong Kong–Macau Expressway, a key north–south artery in China’s national expressway network.
  • D. Tensor G3 chip
    The Tensor G3 chip is Google's custom third-generation mobile processor designed to power Pixel devices with advanced AI, machine learning, and efficiency-focused performance.
  • E. GTC
    GTC is a Polish vehicle registration code assigned to a specific county within the Pomeranian Voivodeship.
  • 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_69d889de677081909b22d2657b1f0292 completed April 10, 2026, 5:25 a.m.
NER Named-entity recognition batch_69e4536d03dc81908b8a58f66657c01a completed April 19, 2026, 4 a.m.
NED1 Entity disambiguation (via context triple) batch_6a01c95009fc81909ab2a341c105b046 completed May 11, 2026, 12:19 p.m.
NEDg Description generation batch_6a01cb6b09648190972d5b26bea7b5bf completed May 11, 2026, 12:28 p.m.
NED2 Entity disambiguation (via description) batch_6a01cbe36900819080ae960724848db8 completed May 11, 2026, 12:30 p.m.
Created at: April 10, 2026, 5:49 a.m.