Triple

T22187001
Position Surface form Disambiguated ID Type / Status
Subject MACRO – Museo d’Arte Contemporanea di Roma E548320 entity
Predicate shortName P43 FINISHED
Object MACRO 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: MACRO | Statement: [MACRO – Museo d’Arte Contemporanea di Roma, shortName, MACRO]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: MACRO
Context triple: [MACRO – Museo d’Arte Contemporanea di Roma, shortName, MACRO]
  • A. MACRO
    MACRO is an American media and entertainment company focused on producing and financing film and television projects that center Black people and other people of color.
  • B. MACRO chosen
    MACRO is a major contemporary art museum in Rome showcasing modern and experimental artworks by Italian and international artists.
  • C. Macro
    Macro was a powerful Roman official who served as praetorian prefect, effectively controlling the imperial guard and wielding significant influence in the politics of the early Roman Empire.
  • D. the macroprosopus
    The Macroprosopus is a kabbalistic term for the transcendent, hidden aspect of the divine associated with the highest sefirah and the primordial divine countenance.
  • E. MACRO-11
    MACRO-11 is the assembly language for DEC's PDP-11 minicomputers, widely used for low-level systems and application programming on RSX-11 and related operating systems.
  • 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_69e11e3e0c7c8190b30d278845e2497e completed April 16, 2026, 5:37 p.m.
NER Named-entity recognition batch_69f12aa8f178819094d1556df5aee5b9 completed April 28, 2026, 9:46 p.m.
Created at: April 16, 2026, 8:35 p.m.