Triple

T2016482
Position Surface form Disambiguated ID Type / Status
Subject Republic of Genoa E44005 entity
Predicate notableColony P160 FINISHED
Object Pera
Pera was a prominent Genoese trading quarter and colony located across the Golden Horn from Constantinople, serving as a key hub for Mediterranean and Black Sea commerce.
 E225870 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: Pera | Statement: [Republic of Genoa, notableColony, Pera]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07 
Target entity: Pera
Context triple: [Republic of Genoa, notableColony, Pera]
  • A. Perka
    Perka is a small settlement located on Car Nicobar Island in the Nicobar district of India’s Andaman and Nicobar Islands.
  • B. La Pera
    La Pera is a small municipality in Catalonia, Spain, best known for housing the Castle of Púbol, once owned by surrealist artist Salvador Dalí and his wife Gala.
  • C. Persenet
    Persenet was an ancient Egyptian queen of the 4th Dynasty, known primarily as a consort of Pharaoh Menkaure.
  • D. Baran
    Baran is a surname most notably associated with Paul Baran, a pioneering engineer of packet-switched networks and early internet technology.
  • E. Neša
    Neša is the ancient name of the city of Kültepe, a major Bronze Age trading center and early Hittite capital in central Anatolia.
  • 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: Pera
Triple: [Republic of Genoa, notableColony, Pera]
Generated description
Pera was a prominent Genoese trading quarter and colony located across the Golden Horn from Constantinople, serving as a key hub for Mediterranean and Black Sea commerce.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07 
Target entity: Pera
Target entity description: Pera was a prominent Genoese trading quarter and colony located across the Golden Horn from Constantinople, serving as a key hub for Mediterranean and Black Sea commerce.
  • A. Perka
    Perka is a small settlement located on Car Nicobar Island in the Nicobar district of India’s Andaman and Nicobar Islands.
  • B. La Pera
    La Pera is a small municipality in Catalonia, Spain, best known for housing the Castle of Púbol, once owned by surrealist artist Salvador Dalí and his wife Gala.
  • C. Persenet
    Persenet was an ancient Egyptian queen of the 4th Dynasty, known primarily as a consort of Pharaoh Menkaure.
  • D. Baran
    Baran is a surname most notably associated with Paul Baran, a pioneering engineer of packet-switched networks and early internet technology.
  • E. Neša
    Neša is the ancient name of the city of Kültepe, a major Bronze Age trading center and early Hittite capital in central Anatolia.
  • 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_69a8891201bc8190aca837be6de41579 completed March 4, 2026, 7:33 p.m.
NER Named-entity recognition batch_69abb8ccdb7c81909f6b3c96f79fcdfc completed March 7, 2026, 5:34 a.m.
NED1 Entity disambiguation (via context triple) batch_69ae0aef0fe88190adf9cd218cf7d8b4 completed March 8, 2026, 11:49 p.m.
NEDg Description generation batch_69ae0c1ea0388190b44af2223517129e completed March 8, 2026, 11:54 p.m.
NED2 Entity disambiguation (via description) batch_69ae0c7719e881909059cef2c513a05a completed March 8, 2026, 11:55 p.m.
Created at: March 4, 2026, 7:38 p.m.