Triple

T3706793
Position Surface form Disambiguated ID Type / Status
Subject Isaac Hayes E80911 entity
Predicate spouse P13 FINISHED
Object Emily Ruth Watson
Emily Ruth Watson is known as the wife of the late American soul musician and actor Isaac Hayes.
E398903 NE FINISHED

How this triple was built (4 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: Emily Ruth Watson | Statement: [Isaac Hayes, spouse, Emily Ruth Watson]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Emily Ruth Watson
Context triple: [Isaac Hayes, spouse, Emily Ruth Watson]
  • A. Rachel Watson
    Rachel Watson is the troubled, alcoholic protagonist of "The Girl on the Train," whose obsession with her former life and the people she observes from her daily commute entangles her in a missing-person investigation.
  • B. Emily Woodruff
    Emily Woodruff was the wife of Canadian-American actor Hume Cronyn and is primarily known for her connection to his life and career.
  • C. Amy Williams
    Amy Williams is a British skeleton racer who won the gold medal at the 2010 Winter Olympics in Vancouver.
  • D. Jennifer Winkley
    Jennifer Winkley is known as the former spouse of acclaimed American novelist Cormac McCarthy.
  • E. Rebecca Howe
    Rebecca Howe is a fictional character on the sitcom "Cheers," known as the ambitious and often neurotic bar manager who replaces Diane Chambers.
  • F. None of above. chosen
  • G. Unsure - the case is ambiguous/there is not enough information to decide.
NEDg Description generation gpt-5.1
Instruction
Generate a one-sentence description of the target entity. 
You are given a context triple in the form (subject, predicate, object), where the object is the target entity. 
# Instructions
Use the triple to infer relevant information about the entity. Describe the entity based on what is most defining, well-known. 
Avoid repeating the information from the triple, unless really essential.
# Response Format
Return only the sentence: "Description: [one-sentence description of the target entity]"
Input
Entity: Emily Ruth Watson
Triple: [Isaac Hayes, spouse, Emily Ruth Watson]
Generated description
Emily Ruth Watson is known as the wife of the late American soul musician and actor Isaac Hayes.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07
Target entity: Emily Ruth Watson
Target entity description: Emily Ruth Watson is known as the wife of the late American soul musician and actor Isaac Hayes.
  • A. Rachel Watson
    Rachel Watson is the troubled, alcoholic protagonist of "The Girl on the Train," whose obsession with her former life and the people she observes from her daily commute entangles her in a missing-person investigation.
  • B. Emily Woodruff
    Emily Woodruff was the wife of Canadian-American actor Hume Cronyn and is primarily known for her connection to his life and career.
  • C. Amy Williams
    Amy Williams is a British skeleton racer who won the gold medal at the 2010 Winter Olympics in Vancouver.
  • D. Jennifer Winkley
    Jennifer Winkley is known as the former spouse of acclaimed American novelist Cormac McCarthy.
  • E. Rebecca Howe
    Rebecca Howe is a fictional character on the sitcom "Cheers," known as the ambitious and often neurotic bar manager who replaces Diane Chambers.
  • F. None of above. chosen

Provenance (5 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_69ad8b1793888190a5f70e4b21dc05a1 completed March 8, 2026, 2:43 p.m.
NER Named-entity recognition batch_69adc57edd748190a006e15fa0248679 completed March 8, 2026, 6:52 p.m.
NED1 Entity disambiguation (via context triple) batch_69b5282613d0819085a47d1fffdaa4d5 completed March 14, 2026, 9:19 a.m.
NEDg Description generation batch_69b5292b13a08190bf23231285adae38 completed March 14, 2026, 9:23 a.m.
NED2 Entity disambiguation (via description) batch_69b529600884819098cb208e38e6281a completed March 14, 2026, 9:24 a.m.
Created at: March 8, 2026, 3:33 p.m.