Triple

T9112580
Position Surface form Disambiguated ID Type / Status
Subject Mark Gatiss E218636 entity
Predicate wrote P2831 FINISHED
Object The Unfriend E779102 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 Unfriend | Statement: [Mark Gatiss, wrote, The Unfriend]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: The Unfriend
Context triple: [Mark Gatiss, wrote, The Unfriend]
  • A. The Unfriend chosen
    The Unfriend is a darkly comic stage play by Mark Gatiss about a seemingly charming stranger whose visit turns increasingly sinister for a middle-class British couple.
  • B. An Interrupted Friendship
    "An Interrupted Friendship" is a lesser-known literary work by Ethel Lilian Voynich, the Irish-born novelist best known for her revolutionary novel "The Gadfly."
  • C. No New Friends
    "No New Friends" is a hip-hop single by DJ Khaled featuring Drake, Rick Ross, and Lil Wayne that emphasizes loyalty to one's existing circle over forming new relationships.
  • D. God Friended Me
    God Friended Me is an American dramedy television series about an outspoken atheist who begins receiving mysterious friend suggestions from a social media account claiming to be God, leading him to intervene in strangers’ lives.
  • E. Nosedive
    Nosedive is a Black Mirror episode that satirically explores a near-future society obsessed with social media ratings and the consequences of living for online approval.
  • 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_69ca83dc94ac8190b9ef42684d36ff39 completed March 30, 2026, 2:08 p.m.
NER Named-entity recognition batch_69cca84b0a048190964f560f78e27cce completed April 1, 2026, 5:08 a.m.
NED1 Entity disambiguation (via context triple) batch_69d047afbc388190905b13582cd59b05 completed April 3, 2026, 11:05 p.m.
Created at: March 30, 2026, 7:16 p.m.