Triple

T18601703
Position Surface form Disambiguated ID Type / Status
Subject Fort Ross E454634 entity
Predicate hasNameInRussian P20560 FINISHED
Object Росс
Росс — это русское название исторического поселения и бывшего русского форта Форт-Росс в Калифорнии, США.
 E1333804 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: Росс | Statement: [Fort Ross, hasNameInRussian, Росс]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07 
Target entity: Росс
Context triple: [Fort Ross, hasNameInRussian, Росс]
  • A. Rost
    Rost is a minor character who appears in the Doctor Who serial "Attack of the Cybermen."
  • B. Rusich
    Rusich is a series of modern Russian metro trains used in several cities’ subway systems, known for their articulated design and improved passenger comfort.
  • C. Ró
    Ró is a shortened given name or nickname derived from the name Róbert.
  • D. Rasshua
    Rasshua is an uninhabited volcanic island in the central Kuril Islands chain of Russia, known for its rugged terrain and active stratovolcano.
  • E. Rossosh
    Rossosh is a town in Voronezh Oblast, Russia, known as a regional center in the country’s southwest.
  • 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: Росс
Triple: [Fort Ross, hasNameInRussian, Росс]
Generated description
Росс — это русское название исторического поселения и бывшего русского форта Форт-Росс в Калифорнии, США.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07 
Target entity: Росс
Target entity description: Росс — это русское название исторического поселения и бывшего русского форта Форт-Росс в Калифорнии, США.
  • A. Rost
    Rost is a minor character who appears in the Doctor Who serial "Attack of the Cybermen."
  • B. Rusich
    Rusich is a series of modern Russian metro trains used in several cities’ subway systems, known for their articulated design and improved passenger comfort.
  • C. Ró
    Ró is a shortened given name or nickname derived from the name Róbert.
  • D. Rasshua
    Rasshua is an uninhabited volcanic island in the central Kuril Islands chain of Russia, known for its rugged terrain and active stratovolcano.
  • E. Rossosh
    Rossosh is a town in Voronezh Oblast, Russia, known as a regional center in the country’s southwest.
  • 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_69d8d38ae7e081908a98df1251842402 completed April 10, 2026, 10:40 a.m.
NER Named-entity recognition batch_69e5475112608190acacc5ac7a08c4a0 completed April 19, 2026, 9:21 p.m.
NED1 Entity disambiguation (via context triple) batch_6a0503837dfc81908ce5eb5e9f1f6a89 completed May 13, 2026, 11:04 p.m.
NEDg Description generation batch_6a0506b8e2e88190aa9c0ead1c05f06a completed May 13, 2026, 11:18 p.m.
NED2 Entity disambiguation (via description) batch_6a050731c3208190a13ecc77eb9ac9ea completed May 13, 2026, 11:20 p.m.
Created at: April 10, 2026, 11:45 a.m.