Triple

T5252017
Position Surface form Disambiguated ID Type / Status
Subject Chalcidice E118609 entity
Predicate hadAncientCity P45087 FINISHED
Object Mende
Mende was an ancient Greek city-state located on the Pallene peninsula of Chalcidice, known in antiquity for its wine and maritime trade.
 E507210 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: Mende | Statement: [Chalcidice, hadAncientCity, Mende]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07 
Target entity: Mende
Context triple: [Chalcidice, hadAncientCity, Mende]
  • A. Mende
    Mende is a small historic town in southern France that serves as the prefecture of the Lozère department in the Occitanie region.
  • B. Mende
    The Mende are one of the largest ethnic groups in Sierra Leone, known for their rich traditions, secret societies, and significant influence on the country’s culture and politics.
  • C. Zemst
    Zemst is a municipality in the Belgian province of Flemish Brabant, located in the Flanders region.
  • D. Bulgari
    Bulgari is a renowned Italian luxury brand celebrated for its high-end jewelry, watches, accessories, and fragrances.
  • E. Kranidi
    Kranidi is a coastal town in the Argolid region of the Peloponnese in Greece, known as a local administrative and commercial center near popular seaside resorts like Porto Heli.
  • 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: Mende
Triple: [Chalcidice, hadAncientCity, Mende]
Generated description
Mende was an ancient Greek city-state located on the Pallene peninsula of Chalcidice, known in antiquity for its wine and maritime trade.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07 
Target entity: Mende
Target entity description: Mende was an ancient Greek city-state located on the Pallene peninsula of Chalcidice, known in antiquity for its wine and maritime trade.
  • A. Mende
    Mende is a small historic town in southern France that serves as the prefecture of the Lozère department in the Occitanie region.
  • B. Mende
    The Mende are one of the largest ethnic groups in Sierra Leone, known for their rich traditions, secret societies, and significant influence on the country’s culture and politics.
  • C. Zemst
    Zemst is a municipality in the Belgian province of Flemish Brabant, located in the Flanders region.
  • D. Bulgari
    Bulgari is a renowned Italian luxury brand celebrated for its high-end jewelry, watches, accessories, and fragrances.
  • E. Kranidi
    Kranidi is a coastal town in the Argolid region of the Peloponnese in Greece, known as a local administrative and commercial center near popular seaside resorts like Porto Heli.
  • 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_69bd446978108190bb5f9c5c23d93f88 completed March 20, 2026, 12:58 p.m.
NER Named-entity recognition batch_69bd84718f788190ab016ea45878b2a7 completed March 20, 2026, 5:31 p.m.
NED1 Entity disambiguation (via context triple) batch_69befe7005308190a659efbd779c314b completed March 21, 2026, 8:24 p.m.
NEDg Description generation batch_69beff4322308190b252820e7213f05e completed March 21, 2026, 8:27 p.m.
NED2 Entity disambiguation (via description) batch_69beffe02d208190b857d6aaa4d85dae completed March 21, 2026, 8:30 p.m.
Created at: March 20, 2026, 1:50 p.m.