Triple

T20325506
Position Surface form Disambiguated ID Type / Status
Subject Frank Farmer E492322 entity
Predicate uncleOf P8496 FINISHED
Object Fletcher Marron NE NERFINISHED

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: Fletcher Marron | Statement: [Frank Farmer, uncleOf, Fletcher Marron]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Fletcher Marron
Context triple: [Frank Farmer, uncleOf, Fletcher Marron]
  • A. Fletcher Marron chosen
    Fletcher Marron is the young son of superstar singer and actress Rachel Marron in the film "The Bodyguard."
  • B. William Bolitho
    William Bolitho was a notable individual interred at Brighton General Cemetery in Melbourne, remembered locally for his prominence in the community.
  • C. Leslie Morshead
    Leslie Morshead was an Australian general best known for commanding the defending forces during the World War II Siege of Tobruk.
  • D. Andrew Cunningham
    Andrew Cunningham was a prominent British Royal Navy admiral of World War II, noted for his leadership in major Mediterranean campaigns and his role in Allied amphibious operations.
  • E. Geoffrey Jellicoe
    Geoffrey Jellicoe was a prominent British landscape architect and garden designer known for his influential 20th-century public and private landscape projects.
  • F. None of above.
  • G. Unsure - the case is ambiguous/there is not enough information to decide.

Provenance (2 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_69e0b4a0134081909113563e1c3ba68a completed April 16, 2026, 10:06 a.m.
NER Named-entity recognition batch_69e6778f20288190b1862d6be61bfb67 completed April 20, 2026, 6:59 p.m.
Created at: April 16, 2026, 11:21 a.m.