Triple

T18817707
Position Surface form Disambiguated ID Type / Status
Subject ACSIS E460180 entity
Predicate supportsInstrument P12724 FINISHED
Object HARP NE NERFINISHED

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: HARP | Statement: [ACSIS, supportsInstrument, HARP]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: HARP
Context triple: [ACSIS, supportsInstrument, HARP]
  • A. HARP chosen
    HARP is a submillimetre heterodyne array receiver used on the James Clerk Maxwell Telescope for high-resolution spectral observations of cold gas in space.
  • B. HAMP
    HAMP is a U.S. government initiative launched after the 2008 financial crisis to help struggling homeowners avoid foreclosure by modifying their mortgage loans to more affordable terms.
  • C. HAP
    HAP is Apple's HomeKit Accessory Protocol, a communication standard that defines how smart home accessories securely interact with Apple devices and the Home app.
  • D. HARV
    HARV is the standard abbreviation used for the Harvard Crimson men's basketball team in collegiate athletics contexts.
  • E. HASP
    HASP (Houston Automatic Spooling Priority) was an early IBM mainframe job entry and spooling system that managed batch workloads and printer output, serving as a foundation for later systems like JES2.
  • F. None of above.
  • G. Unsure - the case is ambiguous/there is not enough information to decide.

Provenance (2 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_69d8dcf94c288190a06dea029ae4b223 completed April 10, 2026, 11:20 a.m.
NER Named-entity recognition batch_69e5a6b7e75c81909bc65cfc61cbe1c6 completed April 20, 2026, 4:08 a.m.
Created at: April 10, 2026, 11:55 a.m.