Triple

T12886771
Position Surface form Disambiguated ID Type / Status
Subject Wilkie Collins E308245 entity
Predicate notableWork P4 FINISHED
Object Antonina
Antonina is a historical novel by Wilkie Collins set in ancient Rome during the Gothic siege of the city.
 E1010435 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: Antonina | Statement: [Wilkie Collins, notableWork, Antonina]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07 
Target entity: Antonina
Context triple: [Wilkie Collins, notableWork, Antonina]
  • A. Antonina
    Antonina was a prominent Byzantine noblewoman and influential wife of the famed general Belisarius, noted for her political acumen and close association with Empress Theodora in the 6th century.
  • B. Antonina
    Antonina is one of the three central women whose intertwined personal and professional lives are followed over several decades in the Soviet drama film "Moscow Does Not Believe in Tears."
  • C. Antónia
    Antónia is a feminine given name commonly used in various European languages, often as a variant of Antonia.
  • D. Gavriella
    Gavriella is a feminine given name, typically considered a variant of Gabriella with similar Hebrew and Italian roots meaning "God is my strength."
  • E. Rositsa
    Rositsa is a river in northern Bulgaria that serves as a significant tributary of the Yantra River.
  • 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: Antonina
Triple: [Wilkie Collins, notableWork, Antonina]
Generated description
Antonina is a historical novel by Wilkie Collins set in ancient Rome during the Gothic siege of the city.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07 
Target entity: Antonina
Target entity description: Antonina is a historical novel by Wilkie Collins set in ancient Rome during the Gothic siege of the city.
  • A. Antonina
    Antonina was a prominent Byzantine noblewoman and influential wife of the famed general Belisarius, noted for her political acumen and close association with Empress Theodora in the 6th century.
  • B. Antonina
    Antonina is one of the three central women whose intertwined personal and professional lives are followed over several decades in the Soviet drama film "Moscow Does Not Believe in Tears."
  • C. Antónia
    Antónia is a feminine given name commonly used in various European languages, often as a variant of Antonia.
  • D. Gavriella
    Gavriella is a feminine given name, typically considered a variant of Gabriella with similar Hebrew and Italian roots meaning "God is my strength."
  • E. Rositsa
    Rositsa is a river in northern Bulgaria that serves as a significant tributary of the Yantra River.
  • 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_69d7bdf7c1f0819098102569a8d8cbf5 completed April 9, 2026, 2:55 p.m.
NER Named-entity recognition batch_69d9714415c08190aa9944b494a3ddad completed April 10, 2026, 9:53 p.m.
NED1 Entity disambiguation (via context triple) batch_69f6af55623081909fd171129f439302 completed May 3, 2026, 2:13 a.m.
NEDg Description generation batch_69f6b02e3b9881909387c1f70176a1bd completed May 3, 2026, 2:17 a.m.
NED2 Entity disambiguation (via description) batch_69f6b11ced30819090f67a0b1e1369aa completed May 3, 2026, 2:21 a.m.
Created at: April 9, 2026, 5:39 p.m.