Triple

T3677905
Position Surface form Disambiguated ID Type / Status
Subject Mulhouse E78039 entity
Predicate river P165 FINISHED
Object Doller
The Doller is a river in northeastern France that flows through the Alsace region and joins the Ill near Mulhouse.
E379012 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: Doller | Statement: [Mulhouse, river, Doller]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Doller
Context triple: [Mulhouse, river, Doller]
  • A. Dollar
    Dollar is a small historic town in Clackmannanshire, Scotland, known for its scenic setting near the Ochil Hills and the nearby Castle Campbell.
  • B. Dollar
    Dollar was a British pop duo, formed by David Van Day and Thereza Bazar, known for their catchy synth-pop hits in the late 1970s and early 1980s.
  • C. US dollar
    The US dollar is the official currency of the United States and the world’s primary reserve currency used widely in global trade and finance.
  • D. Libra
    Libra is a novel by Don DeLillo that offers a fictionalized exploration of the events and conspiracies surrounding the assassination of U.S. President John F. Kennedy.
  • E. USD
    USD (Universal Scene Description) is an open-source 3D scene description and interchange framework developed by Pixar, widely used for creating, composing, and collaborating on complex virtual worlds and assets.
  • 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: Doller
Triple: [Mulhouse, river, Doller]
Generated description
The Doller is a river in northeastern France that flows through the Alsace region and joins the Ill near Mulhouse.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07
Target entity: Doller
Target entity description: The Doller is a river in northeastern France that flows through the Alsace region and joins the Ill near Mulhouse.
  • A. Dollar
    Dollar is a small historic town in Clackmannanshire, Scotland, known for its scenic setting near the Ochil Hills and the nearby Castle Campbell.
  • B. Dollar
    Dollar was a British pop duo, formed by David Van Day and Thereza Bazar, known for their catchy synth-pop hits in the late 1970s and early 1980s.
  • C. US dollar
    The US dollar is the official currency of the United States and the world’s primary reserve currency used widely in global trade and finance.
  • D. Libra
    Libra is a novel by Don DeLillo that offers a fictionalized exploration of the events and conspiracies surrounding the assassination of U.S. President John F. Kennedy.
  • E. USD
    USD (Universal Scene Description) is an open-source 3D scene description and interchange framework developed by Pixar, widely used for creating, composing, and collaborating on complex virtual worlds and assets.
  • 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_69ad85e18c1c8190be8aafb227f39f48 completed March 8, 2026, 2:21 p.m.
NER Named-entity recognition batch_69adc46599188190a046eddb0d85c483 completed March 8, 2026, 6:48 p.m.
NED1 Entity disambiguation (via context triple) batch_69b4c3a50d40819081aad0c72bcaee9d completed March 14, 2026, 2:10 a.m.
NEDg Description generation batch_69b4c451a5048190bfd4675cd17de655 completed March 14, 2026, 2:13 a.m.
NED2 Entity disambiguation (via description) batch_69b4c494ad80819084d6aa10fe62a63b completed March 14, 2026, 2:14 a.m.
Created at: March 8, 2026, 3:25 p.m.