Triple

T15696173
Position Surface form Disambiguated ID Type / Status
Subject Anna Dalassene E380464 entity
Predicate heldTitle P8 FINISHED
Object sebaste
Sebaste was a prestigious Byzantine court title, often granted to high-ranking women of the imperial family to signify their elevated status and influence.
E1170476 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: sebaste | Statement: [Anna Dalassene, heldTitle, sebaste]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: sebaste
Context triple: [Anna Dalassene, heldTitle, sebaste]
  • A. SEBL
    SEBL was the stock ticker symbol for Siebel Systems, a prominent customer relationship management (CRM) software company later acquired by Oracle.
  • B. SEB
    SEB is a major Swedish financial group and bank, historically linked to the influential Wallenberg family and known for its corporate and investment banking services in Northern Europe.
  • C. SEB
    SEB is the IATA airport code for Sabha Airport, which serves the city of Sabha in southwestern Libya.
  • D. SEST
    SEST is the ICAO airport code for San Cristóbal Airport, which serves San Cristóbal Island in the Galápagos, Ecuador.
  • E. SEREB
    SEREB was a French aerospace company involved in the development of ballistic missiles and space launch vehicles before being merged into Aérospatiale.
  • 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: sebaste
Triple: [Anna Dalassene, heldTitle, sebaste]
Generated description
Sebaste was a prestigious Byzantine court title, often granted to high-ranking women of the imperial family to signify their elevated status and influence.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07
Target entity: sebaste
Target entity description: Sebaste was a prestigious Byzantine court title, often granted to high-ranking women of the imperial family to signify their elevated status and influence.
  • A. SEBL
    SEBL was the stock ticker symbol for Siebel Systems, a prominent customer relationship management (CRM) software company later acquired by Oracle.
  • B. SEB
    SEB is a major Swedish financial group and bank, historically linked to the influential Wallenberg family and known for its corporate and investment banking services in Northern Europe.
  • C. SEB
    SEB is the IATA airport code for Sabha Airport, which serves the city of Sabha in southwestern Libya.
  • D. SEST
    SEST is the ICAO airport code for San Cristóbal Airport, which serves San Cristóbal Island in the Galápagos, Ecuador.
  • E. SEREB
    SEREB was a French aerospace company involved in the development of ballistic missiles and space launch vehicles before being merged into Aérospatiale.
  • 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_69d86d99e860819094b6957cde470f2c completed April 10, 2026, 3:25 a.m.
NER Named-entity recognition batch_69e04f50ce848190a839c4fb7306d793 completed April 16, 2026, 2:54 a.m.
NED1 Entity disambiguation (via context triple) batch_69ff6eeeef188190a70aca06ddfe11e6 completed May 9, 2026, 5:29 p.m.
NEDg Description generation batch_69ff6f4c9a008190895fee7abeb62536 completed May 9, 2026, 5:30 p.m.
NED2 Entity disambiguation (via description) batch_69ff6fa74b1c8190a7ceb63943639793 completed May 9, 2026, 5:32 p.m.
Created at: April 10, 2026, 4:44 a.m.