Triple

T9154514
Position Surface form Disambiguated ID Type / Status
Subject The Good Wife E219674 entity
Predicate starring P1507 FINISHED
Object Graham Phillips E370994 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: Graham Phillips | Statement: [The Good Wife, starring, Graham Phillips]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Graham Phillips
Context triple: [The Good Wife, starring, Graham Phillips]
  • A. Graham Phillips chosen
    Graham Phillips is an American actor and director best known for his roles in the TV series "The Good Wife" and films such as "Evan Almighty."
  • B. Graham Sharp
    Graham Sharp is an American banjo player, singer, and songwriter best known as a founding member of the bluegrass band Steep Canyon Rangers.
  • C. Graham Sleight
    Graham Sleight is a British critic and editor best known for his work in science fiction and fantasy literature.
  • D. Anthony Phillips
    Anthony Phillips is an English guitarist and composer best known as a founding member and early guitarist of the rock band Genesis before establishing a prolific solo and library music career.
  • E. Neil Hartley
    Neil Hartley is a film and television producer known for his work on the adaptation of "The Go-Between."
  • 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_69ca83e25418819093c6503deeaf30de completed March 30, 2026, 2:08 p.m.
NER Named-entity recognition batch_69cca96f87ac8190b2fc6d2b2834c1b6 completed April 1, 2026, 5:13 a.m.
NED1 Entity disambiguation (via context triple) batch_69d0484e580c8190944ad76f6ef0be9d completed April 3, 2026, 11:07 p.m.
Created at: March 30, 2026, 7:20 p.m.