Triple

T9999783
Position Surface form Disambiguated ID Type / Status
Subject Nic Mathieu E197293 entity
Predicate directed P7373 FINISHED
Object Spectral E38405 NE 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: Spectral | Statement: [Nic Mathieu, directed, Spectral]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Spectral
Context triple: [Nic Mathieu, directed, Spectral]
  • A. Spectral chosen
    Spectral is a 2016 military science fiction film that follows a special-ops team confronting ghostly entities in a war-torn Eastern European city.
  • B. SPECTRA
    SPECTRA is an advanced integrated electronic warfare and self-protection suite used on modern combat aircraft, notably the Dassault Rafale, to detect, jam, and counter threats.
  • C. Spectrum
    Spectrum is a major American telecommunications brand providing cable television, internet, and phone services, owned by Charter Communications.
  • D. Spectrum
    Spectrum is a collection of essays by historian and political theorist Perry Anderson that surveys and critiques major currents in modern political and intellectual thought.
  • E. Spectrum
    Spectrum was a historic indoor sports and entertainment arena in Philadelphia that hosted professional hockey, basketball, concerts, and major events from the late 1960s until its closure and demolition.
  • F. None of above.
  • G. Unsure - the case is ambiguous/there is not enough information to decide.

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_69ca82f3b61c81908ecc2c1c96dbc2e4 completed March 30, 2026, 2:04 p.m.
NER Named-entity recognition batch_69cdcc8dc9c081909b6d20909ada09cf completed April 2, 2026, 1:55 a.m.
NED1 Entity disambiguation (via context triple) batch_69d26a36aadc81909978b71bdb3a6654 completed April 5, 2026, 1:57 p.m.
Created at: March 30, 2026, 8:51 p.m.