Triple

T15747161
Position Surface form Disambiguated ID Type / Status
Subject Ana Blandiana E381748 entity
Predicate familyName P18 FINISHED
Object Coman
Coman is a Romanian surname, notably borne by the poet and dissident Ana Blandiana (born Otilia Valeria Coman).
 E1174277 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: Coman | Statement: [Ana Blandiana, familyName, Coman]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07 
Target entity: Coman
Context triple: [Ana Blandiana, familyName, Coman]
  • A. Gervinho
    Gervinho is an Ivorian professional footballer known for his pace and dribbling as a winger, who has played for top European clubs and been a key figure for the Ivory Coast national team.
  • B. Mendy
    Mendy is a central, opera-obsessed character in Terrence McNally’s play "The Lisbon Traviata," known for his sharp wit and encyclopedic knowledge of Maria Callas recordings.
  • C. Emmanuel Bailly
    Emmanuel Bailly was a 19th-century French Catholic layman and journalist best known as the founding president and organizer of the Society of Saint Vincent de Paul.
  • D. Nico Leunen
    Nico Leunen is a Belgian film editor known for his work on acclaimed international and arthouse films.
  • E. Ramos
    Ramos is a municipality in the Philippine province of Tarlac known for its predominantly agricultural economy and rural communities.
  • 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: Coman
Triple: [Ana Blandiana, familyName, Coman]
Generated description
Coman is a Romanian surname, notably borne by the poet and dissident Ana Blandiana (born Otilia Valeria Coman).
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07 
Target entity: Coman
Target entity description: Coman is a Romanian surname, notably borne by the poet and dissident Ana Blandiana (born Otilia Valeria Coman).
  • A. Gervinho
    Gervinho is an Ivorian professional footballer known for his pace and dribbling as a winger, who has played for top European clubs and been a key figure for the Ivory Coast national team.
  • B. Mendy
    Mendy is a central, opera-obsessed character in Terrence McNally’s play "The Lisbon Traviata," known for his sharp wit and encyclopedic knowledge of Maria Callas recordings.
  • C. Emmanuel Bailly
    Emmanuel Bailly was a 19th-century French Catholic layman and journalist best known as the founding president and organizer of the Society of Saint Vincent de Paul.
  • D. Nico Leunen
    Nico Leunen is a Belgian film editor known for his work on acclaimed international and arthouse films.
  • E. Ramos
    Ramos is a municipality in the Philippine province of Tarlac known for its predominantly agricultural economy and rural communities.
  • 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_69d86d9e6b44819085d1f6a969ecb74c completed April 10, 2026, 3:25 a.m.
NER Named-entity recognition batch_69e0502d72008190b4d13a6b3a12e467 completed April 16, 2026, 2:57 a.m.
NED1 Entity disambiguation (via context triple) batch_69ff8309cba881909579ee5a62b3aa31 completed May 9, 2026, 6:55 p.m.
NEDg Description generation batch_69ff83d929a48190aea75597b864d210 completed May 9, 2026, 6:58 p.m.
NED2 Entity disambiguation (via description) batch_69ff846436e48190b711da134c9a3b81 completed May 9, 2026, 7 p.m.
Created at: April 10, 2026, 4:46 a.m.