Triple

T1755507
Position Surface form Disambiguated ID Type / Status
Subject Michelle Williams E38536 entity
Predicate hasChild P369 FINISHED
Object Matilda Ledger
Matilda Ledger is the daughter of actors Michelle Williams and the late Heath Ledger.
E196187 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: Matilda Ledger | Statement: [Michelle Williams, hasChild, Matilda Ledger]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Matilda Ledger
Context triple: [Michelle Williams, hasChild, Matilda Ledger]
  • A. Sadie Frost
    Sadie Frost is an English actress, producer, and fashion designer known for her roles in films like "Bram Stoker's Dracula" and for co-founding the fashion label Frost French.
  • B. Isla Dawson
    Isla Dawson is a remote Chilean island in southern Patagonia, located within the Strait of Magellan and known for its harsh climate and historical use as a mission and penal colony.
  • C. Tamsin Wise
    Tamsin Wise is a member of the Wise family, related to British actor and producer Greg Wise.
  • D. Grace Gummer
    Grace Gummer is an American actress known for her work in film, television, and theater, including roles in series like "Mr. Robot" and "The Newsroom."
  • E. Tessa Menzies
    Tessa Menzies is a child of California politician and governor Gavin Newsom.
  • 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: Matilda Ledger
Triple: [Michelle Williams, hasChild, Matilda Ledger]
Generated description
Matilda Ledger is the daughter of actors Michelle Williams and the late Heath Ledger.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07
Target entity: Matilda Ledger
Target entity description: Matilda Ledger is the daughter of actors Michelle Williams and the late Heath Ledger.
  • A. Sadie Frost
    Sadie Frost is an English actress, producer, and fashion designer known for her roles in films like "Bram Stoker's Dracula" and for co-founding the fashion label Frost French.
  • B. Isla Dawson
    Isla Dawson is a remote Chilean island in southern Patagonia, located within the Strait of Magellan and known for its harsh climate and historical use as a mission and penal colony.
  • C. Tamsin Wise
    Tamsin Wise is a member of the Wise family, related to British actor and producer Greg Wise.
  • D. Grace Gummer
    Grace Gummer is an American actress known for her work in film, television, and theater, including roles in series like "Mr. Robot" and "The Newsroom."
  • E. Tessa Menzies
    Tessa Menzies is a child of California politician and governor Gavin Newsom.
  • 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_69a8862bdb2081908aefe831c8aa8017 completed March 4, 2026, 7:21 p.m.
NER Named-entity recognition batch_69aa643b623081908064be75758ec5de completed March 6, 2026, 5:20 a.m.
NED1 Entity disambiguation (via context triple) batch_69ada0ea4cc08190b47d81a54c294a9a completed March 8, 2026, 4:16 p.m.
NEDg Description generation batch_69ada1a401548190af00bae3b89e46b0 completed March 8, 2026, 4:19 p.m.
NED2 Entity disambiguation (via description) batch_69ada26804288190838a93b71b494650 completed March 8, 2026, 4:23 p.m.
Created at: March 4, 2026, 7:31 p.m.