Triple

T11388423
Position Surface form Disambiguated ID Type / Status
Subject Fritz Lang E269767 entity
Predicate spouse P13 FINISHED
Object Lily Latte
Lily Latte was the first wife of influential Austrian-German filmmaker Fritz Lang, known primarily in relation to his early personal life.
E923425 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: Lily Latte | Statement: [Fritz Lang, spouse, Lily Latte]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Lily Latte
Context triple: [Fritz Lang, spouse, Lily Latte]
  • A. Lassik
    Lassik is an extinct Athabaskan language once spoken by the Lassik people in northern California.
  • B. Georgia Latte Nista
    Georgia Latte Nista is a ready-to-drink canned latte beverage sold under the Georgia Coffee brand.
  • C. Pierrelatte
    Pierrelatte is a commune in southeastern France known for its proximity to the Tricastin nuclear complex and its location in the Drôme department of the Auvergne-Rhône-Alpes region.
  • D. Limonada
    Limonada is a studio album by Puerto Rican singer-songwriter Kany García, known for its blend of Latin pop and introspective, emotionally rich songwriting.
  • E. Latte Pronto
    Latte Pronto is the central protagonist of the work "Fool's Paradise," around whom the story's main events and conflicts revolve.
  • 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: Lily Latte
Triple: [Fritz Lang, spouse, Lily Latte]
Generated description
Lily Latte was the first wife of influential Austrian-German filmmaker Fritz Lang, known primarily in relation to his early personal life.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07
Target entity: Lily Latte
Target entity description: Lily Latte was the first wife of influential Austrian-German filmmaker Fritz Lang, known primarily in relation to his early personal life.
  • A. Lassik
    Lassik is an extinct Athabaskan language once spoken by the Lassik people in northern California.
  • B. Georgia Latte Nista
    Georgia Latte Nista is a ready-to-drink canned latte beverage sold under the Georgia Coffee brand.
  • C. Pierrelatte
    Pierrelatte is a commune in southeastern France known for its proximity to the Tricastin nuclear complex and its location in the Drôme department of the Auvergne-Rhône-Alpes region.
  • D. Limonada
    Limonada is a studio album by Puerto Rican singer-songwriter Kany García, known for its blend of Latin pop and introspective, emotionally rich songwriting.
  • E. Latte Pronto
    Latte Pronto is the central protagonist of the work "Fool's Paradise," around whom the story's main events and conflicts revolve.
  • 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_69d6aacdbc6c8190af6dc3d5f5d22836 completed April 8, 2026, 7:21 p.m.
NER Named-entity recognition batch_69d7fc389d4c81909515a5c8b0099c36 completed April 9, 2026, 7:21 p.m.
NED1 Entity disambiguation (via context triple) batch_69e58c672da48190affacc0f19ef0c7a completed April 20, 2026, 2:16 a.m.
NEDg Description generation batch_69e59774e6648190a38b2515a83c2e0c completed April 20, 2026, 3:03 a.m.
NED2 Entity disambiguation (via description) batch_69e5a3abf24481908fb71f4ef6b13532 completed April 20, 2026, 3:55 a.m.
Created at: April 8, 2026, 9:34 p.m.