Triple

T3301292
Position Surface form Disambiguated ID Type / Status
Subject Southpaw E69336 entity
Predicate starring P1507 FINISHED
Object Jake Gyllenhaal E303090 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: Jake Gyllenhaal | Statement: [Southpaw, starring, Jake Gyllenhaal]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Jake Gyllenhaal
Context triple: [Southpaw, starring, Jake Gyllenhaal]
  • A. Jake Gyllenhaal chosen
    Jake Gyllenhaal is an acclaimed American actor known for his intense, versatile performances in films ranging from independent dramas to major studio thrillers.
  • B. Emile Hirsch
    Emile Hirsch is an American actor known for his intense performances in films such as "Into the Wild," "Milk," and "Lone Survivor."
  • C. Logan Lerman
    Logan Lerman is an American actor best known for his lead role in the "Percy Jackson" film series and performances in movies such as "The Perks of Being a Wallflower" and "Fury."
  • D. Taylor Kitsch
    Taylor Kitsch is a Canadian actor best known for his breakout role as Tim Riggins on the television series "Friday Night Lights" and for starring in films such as "John Carter" and "Lone Survivor."
  • E. Garrett Hedlund
    Garrett Hedlund is an American actor and singer known for roles in films such as "Tron: Legacy," "Friday Night Lights," and "Country Strong."
  • 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_69ad859e529c8190a404273f53cb487d completed March 8, 2026, 2:20 p.m.
NER Named-entity recognition batch_69adb0a7d224819080d9a638e08bb8a8 completed March 8, 2026, 5:23 p.m.
NED1 Entity disambiguation (via context triple) batch_69b2f3df7f548190ada47f742df46545 completed March 12, 2026, 5:11 p.m.
Created at: March 8, 2026, 3:11 p.m.