Triple

T30843706
Position Surface form Disambiguated ID Type / Status
Subject K1 E785578 entity
Predicate powerReserve P129157 FINISHED
Object approximately 30 hours 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: approximately 30 hours | Statement: [K1, powerReserve, approximately 30 hours]
PD Predicate disambiguation gpt-5-mini-2025-08-07
Target predicate: powerReserve
Context triple: [K1, powerReserve, approximately 30 hours]
  • A. hasBackupBattery
    Indicates that an entity is equipped with an additional battery intended to provide power when the primary power source is unavailable or fails.
  • B. powerDuration chosen
    Indicates the length of time for which a power, ability, or effect remains active or in force.
  • C. reservesPowerTo
    Indicates that one party retains or explicitly keeps for itself the authority or right to exercise a particular power or function, rather than granting it to others.
  • D. batteryLife
    Indicates how long a device can operate on a single charge or set of batteries before needing to be recharged or replaced.
  • E. powerCondition
    Indicates that one entity’s ability to function, operate, or exert influence depends on a specified power-related requirement or state being satisfied.
  • F. None of above.

Provenance (3 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_69f224b850848190a4af4ccf8ddadcdf completed April 29, 2026, 3:33 p.m.
NER Named-entity recognition batch_69f73ae120bc8190bff94d38d7a7a00d completed May 3, 2026, 12:09 p.m.
PD Predicate disambiguation batch_69f73a38d0848190aa5139144b8561c6 completed May 3, 2026, 12:06 p.m.
Created at: April 29, 2026, 8:46 p.m.