Triple

T15711989
Position Surface form Disambiguated ID Type / Status
Subject It Follows E380860 entity
Predicate cinematographyBy P1953 FINISHED
Object Mike Gioulakis E671194 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: Mike Gioulakis | Statement: [It Follows, cinematographyBy, Mike Gioulakis]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Mike Gioulakis
Context triple: [It Follows, cinematographyBy, Mike Gioulakis]
  • A. Mike Gioulakis chosen
    Mike Gioulakis is an American cinematographer known for his visually striking work on films such as "It Follows," "Split," and "Glass."
  • B. Jimmy Giannos
    Jimmy Giannos is an author best known for writing the work titled "Intentions."
  • C. Nick Patsaouras
    Nick Patsaouras is a Greek-American engineer and public transportation advocate known for his influential role in shaping transit policy and infrastructure in Los Angeles.
  • D. Andrew Vassiliadis
    Andrew Vassiliadis is an American businessman and sports executive best known for owning and leading the USL Championship soccer club San Diego Loyal SC.
  • E. Michael Spartali
    Michael Spartali was a 19th-century Anglo-Greek merchant and prominent member of the London Greek community, best known as the father of Pre-Raphaelite painter Marie Spartali Stillman.
  • 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_69d86d9bf930819082b30cf6d169297c completed April 10, 2026, 3:25 a.m.
NER Named-entity recognition batch_69e04f8f5d6081908243fa59b46b7c76 completed April 16, 2026, 2:55 a.m.
NED1 Entity disambiguation (via context triple) batch_69ff757f571881908015fe68df2a5e69 completed May 9, 2026, 5:57 p.m.
Created at: April 10, 2026, 4:45 a.m.