Triple

T21571665
Position Surface form Disambiguated ID Type / Status
Subject Amédée Courbet E532297 entity
Predicate deathPlace P21 FINISHED
Object Makung
Makung (now commonly spelled Magong) is the principal city of Taiwan’s Penghu (Pescadores) archipelago, historically significant as a strategic naval and trading port in the Taiwan Strait.
 E1491852 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: Makung | Statement: [Amédée Courbet, deathPlace, Makung]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07 
Target entity: Makung
Context triple: [Amédée Courbet, deathPlace, Makung]
  • A. Ikan
    Ikan is an alternative name for the Ukaan language, a lesser-known Niger-Congo language spoken in parts of Nigeria.
  • B. Lamut
    Lamut is an indigenous Siberian people of northeastern Russia, more commonly known as the Even.
  • C. Bichir
    Bichir is a Mexican acting family name most prominently associated with acclaimed actor Demián Bichir and his relatives in film and television.
  • D. Lipar
    Lipar is a small settlement located within the municipality of Kula in Serbia.
  • E. Huso
    Huso is a small genus of large predatory sturgeons known for species such as the beluga sturgeon, valued for its caviar.
  • 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: Makung
Triple: [Amédée Courbet, deathPlace, Makung]
Generated description
Makung (now commonly spelled Magong) is the principal city of Taiwan’s Penghu (Pescadores) archipelago, historically significant as a strategic naval and trading port in the Taiwan Strait.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07 
Target entity: Makung
Target entity description: Makung (now commonly spelled Magong) is the principal city of Taiwan’s Penghu (Pescadores) archipelago, historically significant as a strategic naval and trading port in the Taiwan Strait.
  • A. Ikan
    Ikan is an alternative name for the Ukaan language, a lesser-known Niger-Congo language spoken in parts of Nigeria.
  • B. Lamut
    Lamut is an indigenous Siberian people of northeastern Russia, more commonly known as the Even.
  • C. Bichir
    Bichir is a Mexican acting family name most prominently associated with acclaimed actor Demián Bichir and his relatives in film and television.
  • D. Lipar
    Lipar is a small settlement located within the municipality of Kula in Serbia.
  • E. Huso
    Huso is a small genus of large predatory sturgeons known for species such as the beluga sturgeon, valued for its caviar.
  • 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_69e0c460db088190828c64206a450273 completed April 16, 2026, 11:13 a.m.
NER Named-entity recognition batch_69eee9cd50188190b44eb25fb87312bb completed April 27, 2026, 4:45 a.m.
NED1 Entity disambiguation (via context triple) batch_6a09f672b5808190a2dd61c26ce64403 completed May 17, 2026, 5:10 p.m.
NEDg Description generation batch_6a09f78a3d788190b4b19f3b6463550e completed May 17, 2026, 5:14 p.m.
NED2 Entity disambiguation (via description) batch_6a09f825b02c819096f57b1dba02ded2 completed May 17, 2026, 5:17 p.m.
Created at: April 16, 2026, 6:30 p.m.