Triple

T9291815
Position Surface form Disambiguated ID Type / Status
Subject Tériade E223536 entity
Predicate givenName P17 FINISHED
Object Stratis
Stratis is the given name of Tériade, a notable Greek-born art critic and publisher known for collaborating with major 20th-century artists.
 E790727 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: Stratis | Statement: [Tériade, givenName, Stratis]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07 
Target entity: Stratis
Context triple: [Tériade, givenName, Stratis]
  • A. Telesia
    Telesia was an important ancient town in the region of Samnium in south-central Italy, known for its strategic and military significance in pre-Roman and Roman times.
  • B. Telos
    Telos is an icy, subterranean planet in the Doctor Who universe best known as a major stronghold and tomb world of the Cybermen.
  • C. Iolkos
    Iolkos was an ancient city in Thessaly, Greece, traditionally known as the homeland of Jason and the starting point of the Argonauts’ voyage in Greek mythology.
  • D. Soter
    Soter is a Greek term meaning "savior" or "deliverer," often used as a title for deities or revered figures who provide salvation or protection.
  • E. Teku
    Teku is an open-source Ethereum consensus client written in Java, designed to run Ethereum proof-of-stake validators in a secure and enterprise-friendly way.
  • 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: Stratis
Triple: [Tériade, givenName, Stratis]
Generated description
Stratis is the given name of Tériade, a notable Greek-born art critic and publisher known for collaborating with major 20th-century artists.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07 
Target entity: Stratis
Target entity description: Stratis is the given name of Tériade, a notable Greek-born art critic and publisher known for collaborating with major 20th-century artists.
  • A. Telesia
    Telesia was an important ancient town in the region of Samnium in south-central Italy, known for its strategic and military significance in pre-Roman and Roman times.
  • B. Telos
    Telos is an icy, subterranean planet in the Doctor Who universe best known as a major stronghold and tomb world of the Cybermen.
  • C. Iolkos
    Iolkos was an ancient city in Thessaly, Greece, traditionally known as the homeland of Jason and the starting point of the Argonauts’ voyage in Greek mythology.
  • D. Soter
    Soter is a Greek term meaning "savior" or "deliverer," often used as a title for deities or revered figures who provide salvation or protection.
  • E. Teku
    Teku is an open-source Ethereum consensus client written in Java, designed to run Ethereum proof-of-stake validators in a secure and enterprise-friendly way.
  • 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_69ca8422ddf881908a3f8f876c9f53aa completed March 30, 2026, 2:09 p.m.
NER Named-entity recognition batch_69cd0866ff608190a07afac4afd0ec09 completed April 1, 2026, 11:58 a.m.
NED1 Entity disambiguation (via context triple) batch_69d0b2381e2c8190acbecf97dea1200c completed April 4, 2026, 6:39 a.m.
NEDg Description generation batch_69d0b3a2b6f481908b0528f6fa67535b completed April 4, 2026, 6:45 a.m.
NED2 Entity disambiguation (via description) batch_69d0b7944adc819080b3a90878dd7203 completed April 4, 2026, 7:02 a.m.
Created at: March 30, 2026, 7:35 p.m.