Triple

T36933748
Position Surface form Disambiguated ID Type / Status
Subject iPad Pro (11-inch, 1st generation) E913554 entity
Predicate higherRAMAppliesTo P194967 FINISHED
Object 1 TB storage model LITERAL FINISHED

How this triple was built (2 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: 1 TB storage model | Statement: [iPad Pro (11-inch, 1st generation), higherRAMAppliesTo, 1 TB storage model]
PD Predicate disambiguation gpt-5-mini-2025-08-07
Target predicate: higherRAMAppliesTo
Context triple: [iPad Pro (11-inch, 1st generation), higherRAMAppliesTo, 1 TB storage model]
  • A. hasRAM
    Indicates that an entity possesses or is equipped with a specified amount or type of random-access memory (RAM).
  • B. typicalRAMRange
    Indicates the usual or commonly expected range of RAM capacity associated with an entity.
  • C. expandableRAM
    Indicates that a device’s RAM can be increased beyond its original capacity, typically by adding or upgrading memory modules.
  • D. typicalRAMRangeMB
    Indicates the usual or expected range of RAM capacity, measured in megabytes, associated with an entity.
  • E. videoRAMUpgradeable
    Indicates that the amount of video RAM in a device can be increased or replaced beyond its original configuration.
  • F. None of above. chosen

Provenance (4 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_69f76e896c988190880c130e01303dd4 completed May 3, 2026, 3:49 p.m.
NER Named-entity recognition batch_69fd91a5dad8819093eeeef527027890 completed May 8, 2026, 7:32 a.m.
PD Predicate disambiguation batch_69fd8f65fe9081908902500a3228d935 completed May 8, 2026, 7:23 a.m.
PDg Predicate description generation batch_69fd91a44268819081b372296e3aa116 completed May 8, 2026, 7:32 a.m.
Created at: May 3, 2026, 4:13 p.m.