Triple

T5828744
Position Surface form Disambiguated ID Type / Status
Subject Paris Métro Line 9 E129292 entity
Predicate station P726 FINISHED
Object Michel-Ange–Molitor
Michel-Ange–Molitor is a Paris Métro station in the 16th arrondissement that serves as an interchange between lines 9 and 10.
 E548775 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: Michel-Ange–Molitor | Statement: [Paris Métro Line 9, station, Michel-Ange–Molitor]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07 
Target entity: Michel-Ange–Molitor
Context triple: [Paris Métro Line 9, station, Michel-Ange–Molitor]
  • A. Michel
    Michel is a fictional character appearing in Frederick Forsyth’s political thriller novel "The Dogs of War."
  • B. Michel
    Michel is the birth name of the acclaimed Egyptian actor Omar Sharif, renowned for his roles in classic films such as "Lawrence of Arabia" and "Doctor Zhivago."
  • C. Michel
    Michel is a French given name commonly used for males, equivalent to "Michael" in English.
  • D. Fuselli
    Fuselli is a central fictional character in the World War I novel "Active Service" by Stephen Crane, representing the experiences and attitudes of an ordinary soldier.
  • E. Firmin
    Firmin is a French given name notably borne by Firmin Didot, a renowned printer, typefounder, and member of the influential Didot family in the history of typography.
  • 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: Michel-Ange–Molitor
Triple: [Paris Métro Line 9, station, Michel-Ange–Molitor]
Generated description
Michel-Ange–Molitor is a Paris Métro station in the 16th arrondissement that serves as an interchange between lines 9 and 10.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07 
Target entity: Michel-Ange–Molitor
Target entity description: Michel-Ange–Molitor is a Paris Métro station in the 16th arrondissement that serves as an interchange between lines 9 and 10.
  • A. Michel
    Michel is a fictional character appearing in Frederick Forsyth’s political thriller novel "The Dogs of War."
  • B. Michel
    Michel is the birth name of the acclaimed Egyptian actor Omar Sharif, renowned for his roles in classic films such as "Lawrence of Arabia" and "Doctor Zhivago."
  • C. Michel
    Michel is a French given name commonly used for males, equivalent to "Michael" in English.
  • D. Fuselli
    Fuselli is a central fictional character in the World War I novel "Active Service" by Stephen Crane, representing the experiences and attitudes of an ordinary soldier.
  • E. Firmin
    Firmin is a French given name notably borne by Firmin Didot, a renowned printer, typefounder, and member of the influential Didot family in the history of typography.
  • 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_69c00849d55481908b4f9f5543e0bf6d completed March 22, 2026, 3:18 p.m.
NER Named-entity recognition batch_69c03467dfe48190b51757b33681bc20 completed March 22, 2026, 6:26 p.m.
NED1 Entity disambiguation (via context triple) batch_69c09863be3c8190bba357bf64e22917 completed March 23, 2026, 1:33 a.m.
NEDg Description generation batch_69c098d936d081909d930fc8b6b3fd67 completed March 23, 2026, 1:35 a.m.
NED2 Entity disambiguation (via description) batch_69c09947c5fc8190ba279ed0f991f9a9 completed March 23, 2026, 1:37 a.m.
Created at: March 22, 2026, 3:53 p.m.