Triple

T907185
Position Surface form Disambiguated ID Type / Status
Subject Alsace E19573 entity
Predicate traditionalDish P19483 FINISHED
Object flammekueche
Flammekueche is a thin-crusted Alsatian tart typically topped with crème fraîche, onions, and bacon, similar to a rustic pizza.
 E107184 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: flammekueche | Statement: [Alsace, traditionalDish, flammekueche]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07 
Target entity: flammekueche
Context triple: [Alsace, traditionalDish, flammekueche]
  • A. Frisch
    Frisch is a German-language surname most notably associated with Swiss playwright and novelist Max Frisch.
  • B. WOK
    WOK is the National Rail station code for Woking railway station in Surrey, England.
  • C. Blodgett
    Blodgett is a surname of English origin borne by various notable individuals across fields such as politics, business, and the arts.
  • D. Wiener Schnitzel
    Wiener Schnitzel is a traditional Austrian dish consisting of a thin, breaded and fried veal cutlet, closely associated with Viennese cuisine.
  • E. Nuremberg bratwurst
    Nuremberg bratwurst is a traditional small, thin German sausage from Nuremberg, typically made from finely ground pork and seasoned with marjoram, often grilled and served in multiples.
  • 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: flammekueche
Triple: [Alsace, traditionalDish, flammekueche]
Generated description
Flammekueche is a thin-crusted Alsatian tart typically topped with crème fraîche, onions, and bacon, similar to a rustic pizza.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07 
Target entity: flammekueche
Target entity description: Flammekueche is a thin-crusted Alsatian tart typically topped with crème fraîche, onions, and bacon, similar to a rustic pizza.
  • A. Frisch
    Frisch is a German-language surname most notably associated with Swiss playwright and novelist Max Frisch.
  • B. WOK
    WOK is the National Rail station code for Woking railway station in Surrey, England.
  • C. Blodgett
    Blodgett is a surname of English origin borne by various notable individuals across fields such as politics, business, and the arts.
  • D. Wiener Schnitzel
    Wiener Schnitzel is a traditional Austrian dish consisting of a thin, breaded and fried veal cutlet, closely associated with Viennese cuisine.
  • E. Nuremberg bratwurst
    Nuremberg bratwurst is a traditional small, thin German sausage from Nuremberg, typically made from finely ground pork and seasoned with marjoram, often grilled and served in multiples.
  • 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_69a4939e889c8190ac148b3ac1a7f90b completed March 1, 2026, 7:29 p.m.
NER Named-entity recognition batch_69a4b2cc85a08190bc8186eb9ed1fa38 completed March 1, 2026, 9:42 p.m.
NED1 Entity disambiguation (via context triple) batch_69a7c73b3a848190859df2eed9a21fc5 completed March 4, 2026, 5:46 a.m.
NEDg Description generation batch_69a7c88607648190b7d4e6dd3ec3ad02 completed March 4, 2026, 5:52 a.m.
NED2 Entity disambiguation (via description) batch_69a7c90fe7fc819086070e7c3845e880 completed March 4, 2026, 5:54 a.m.
Created at: March 1, 2026, 7:39 p.m.