Triple

T3219490
Position Surface form Disambiguated ID Type / Status
Subject Genoese colonies in Crimea E67475 entity
Predicate hasPart P35 FINISHED
Object Soldaia
Soldaia was a medieval Genoese trading colony and port settlement located on the Crimean coast of the Black Sea.
 E337660 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: Soldaia | Statement: [Genoese colonies in Crimea, hasPart, Soldaia]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07 
Target entity: Soldaia
Context triple: [Genoese colonies in Crimea, hasPart, Soldaia]
  • A. Odintsovo
    Odintsovo is a town in western Russia that serves as an important suburban center just outside Moscow.
  • B. Soligalich
    Soligalich is a historic Russian town known for its preserved 18th–19th century architecture and location along the Kostroma River in Kostroma Oblast.
  • C. Shughni
    Shughni is an Eastern Iranian language spoken primarily in the Badakhshan region of Tajikistan and Afghanistan, known for its use among the Shughni people in the Pamir Mountains.
  • D. Kirovakan
    Kirovakan is the former name of Vanadzor, a major industrial city in northern Armenia.
  • E. Samokov
    Samokov is a Bulgarian town in the Rila Mountains known historically for its ironworking and as a gateway to nearby ski and hiking areas.
  • 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: Soldaia
Triple: [Genoese colonies in Crimea, hasPart, Soldaia]
Generated description
Soldaia was a medieval Genoese trading colony and port settlement located on the Crimean coast of the Black Sea.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07 
Target entity: Soldaia
Target entity description: Soldaia was a medieval Genoese trading colony and port settlement located on the Crimean coast of the Black Sea.
  • A. Oreshek
    Oreshek is the historic Russian fortress on Lake Ladoga that later gave rise to the town of Shlisselburg.
  • B. Odintsovo
    Odintsovo is a town in western Russia that serves as an important suburban center just outside Moscow.
  • C. Soligalich
    Soligalich is a historic Russian town known for its preserved 18th–19th century architecture and location along the Kostroma River in Kostroma Oblast.
  • D. Shughni
    Shughni is an Eastern Iranian language spoken primarily in the Badakhshan region of Tajikistan and Afghanistan, known for its use among the Shughni people in the Pamir Mountains.
  • E. Kirovakan
    Kirovakan is the former name of Vanadzor, a major industrial city in northern Armenia.
  • 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_69ad858b8adc8190ad989712c87a476b completed March 8, 2026, 2:19 p.m.
NER Named-entity recognition batch_69adab0ef2c88190ab89e3217438a2bf completed March 8, 2026, 4:59 p.m.
NED1 Entity disambiguation (via context triple) batch_69b26245dfb08190a051ec6d2dbc63c6 completed March 12, 2026, 6:50 a.m.
NEDg Description generation batch_69b264c54c508190be85da879935e7f4 completed March 12, 2026, 7:01 a.m.
NED2 Entity disambiguation (via description) batch_69b268d60bd0819097194da2e9065947 completed March 12, 2026, 7:18 a.m.
Created at: March 8, 2026, 3:08 p.m.