Triple

T4488504
Position Surface form Disambiguated ID Type / Status
Subject Lee Patrick E107307 entity
Predicate spouse P13 FINISHED
Object Thomas Wood
Thomas Wood is known primarily as the husband of American character actor Lee Patrick.
E446624 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: Thomas Wood | Statement: [Lee Patrick, spouse, Thomas Wood]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Thomas Wood
Context triple: [Lee Patrick, spouse, Thomas Wood]
  • A. Martin Franklin
    Martin Franklin is a British-born entrepreneur and investor best known for founding Jarden Corporation and leading numerous successful consumer-brands and SPAC ventures.
  • B. John Wilson
    John Wilson is a film editor best known for his work on the visually striking 1989 British-French crime drama "The Cook, the Thief, His Wife & Her Lover."
  • C. James Church
    James Church is the pseudonym of a former Western intelligence officer known for his critically acclaimed Inspector O series of detective novels set in North Korea.
  • D. Andrew Taylor
    Andrew Taylor is a prominent American business executive best known as the longtime leader and former CEO of Enterprise Holdings, the parent company of Enterprise Rent-A-Car.
  • E. John Adam
    John Adam was a member of the prominent Adam family of Scottish architects and designers in the 18th century.
  • 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: Thomas Wood
Triple: [Lee Patrick, spouse, Thomas Wood]
Generated description
Thomas Wood is known primarily as the husband of American character actor Lee Patrick.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07
Target entity: Thomas Wood
Target entity description: Thomas Wood is known primarily as the husband of American character actor Lee Patrick.
  • A. Martin Franklin
    Martin Franklin is a British-born entrepreneur and investor best known for founding Jarden Corporation and leading numerous successful consumer-brands and SPAC ventures.
  • B. John Wilson
    John Wilson is a film editor best known for his work on the visually striking 1989 British-French crime drama "The Cook, the Thief, His Wife & Her Lover."
  • C. James Church
    James Church is the pseudonym of a former Western intelligence officer known for his critically acclaimed Inspector O series of detective novels set in North Korea.
  • D. Andrew Taylor
    Andrew Taylor is a prominent American business executive best known as the longtime leader and former CEO of Enterprise Holdings, the parent company of Enterprise Rent-A-Car.
  • E. John Adam
    John Adam was a member of the prominent Adam family of Scottish architects and designers in the 18th century.
  • 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_69bd43f84f788190a1383579c4a595be completed March 20, 2026, 12:56 p.m.
NER Named-entity recognition batch_69bd52ad36748190b791de458f2116b2 completed March 20, 2026, 1:59 p.m.
NED1 Entity disambiguation (via context triple) batch_69bd67a31d0c819089954c8af4b1bdd6 completed March 20, 2026, 3:28 p.m.
NEDg Description generation batch_69bd69faac508190863892c9bbdb20b3 completed March 20, 2026, 3:38 p.m.
NED2 Entity disambiguation (via description) batch_69bd6a64c64881909acf1171be426fe4 completed March 20, 2026, 3:40 p.m.
Created at: March 20, 2026, 12:59 p.m.