Triple

T16590842
Position Surface form Disambiguated ID Type / Status
Subject Steven Haft E403079 entity
Predicate notableWork P4 FINISHED
Object The Pact E102786 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: The Pact | Statement: [Steven Haft, notableWork, The Pact]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: The Pact
Context triple: [Steven Haft, notableWork, The Pact]
  • A. The Pact
    The Pact is a bestselling novel by Jodi Picoult that explores the aftermath of a tragic teen suicide pact and the complex moral, legal, and emotional questions it raises for the families involved.
  • B. The Pact chosen
    The Pact is a 2012 supernatural horror film that follows a woman uncovering dark secrets in her childhood home after her sister mysteriously disappears.
  • C. the Pact
    The Pact is a legendary agreement in the world of *A Song of Ice and Fire* that ended the ancient war between the Children of the Forest and the First Men by dividing the lands of Westeros between them.
  • D. A Pact
    "A Pact" is a notable poem by Ezra Pound in which he addresses and reconciles with the influence of Walt Whitman on his own poetic development.
  • E. Le Pacte
    Le Pacte is a French film distribution company known for releasing a wide range of independent and auteur cinema.
  • 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_69d88387363c8190a97a0c942130de97 completed April 10, 2026, 4:58 a.m.
NER Named-entity recognition batch_69e359a012e081909a0604dde3c04bbb completed April 18, 2026, 10:14 a.m.
NED1 Entity disambiguation (via context triple) batch_6a00759b9e5081909815d2cd00d44490 completed May 10, 2026, 12:10 p.m.
Created at: April 10, 2026, 5:16 a.m.