Triple

T22718345
Position Surface form Disambiguated ID Type / Status
Subject Orlando (Handel) E561792 entity
Predicate workTitle P24259 FINISHED
Object Orlando
Orlando is an opera seria by George Frideric Handel, first performed in 1733 and based on episodes from Ludovico Ariosto’s epic poem "Orlando Furioso."
E1557335 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: Orlando | Statement: [Orlando (Handel), workTitle, Orlando]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Orlando
Context triple: [Orlando (Handel), workTitle, Orlando]
  • A. Orlando
    Orlando is a major city in central Florida known for its theme parks, tourism industry, and entertainment attractions.
  • B. Orlando
    Orlando is a historic township area within Soweto, South Africa, known for its central role in the anti-apartheid struggle and vibrant local culture.
  • C. Orlando
    Orlando is a common Italian surname borne by numerous individuals, including notable political and cultural figures.
  • D. Orlando
    Orlando is a 1992 British period fantasy film, based on Virginia Woolf’s novel, in which Tilda Swinton plays an androgynous noble who lives for centuries while changing gender.
  • E. Orlando
    Orlando is the Italian literary counterpart of the medieval knight Roland, best known as the chivalric hero of epic poems such as "Orlando Furioso."
  • 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: Orlando
Triple: [Orlando (Handel), workTitle, Orlando]
Generated description
Orlando is an opera seria by George Frideric Handel, first performed in 1733 and based on episodes from Ludovico Ariosto’s epic poem "Orlando Furioso."
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07
Target entity: Orlando
Target entity description: Orlando is an opera seria by George Frideric Handel, first performed in 1733 and based on episodes from Ludovico Ariosto’s epic poem "Orlando Furioso."
  • A. Orlando
    Orlando is the Italian literary counterpart of the medieval knight Roland, best known as the chivalric hero of epic poems such as "Orlando Furioso."
  • B. Orlando
    Orlando is the young, virtuous, and romantically idealistic hero of Shakespeare’s comedy "As You Like It," known for his love for Rosalind and his conflict with his elder brother.
  • C. Orlando
    Orlando is a 1992 British period fantasy film, based on Virginia Woolf’s novel, in which Tilda Swinton plays an androgynous noble who lives for centuries while changing gender.
  • D. Orlando
    Orlando is a common Italian surname borne by numerous individuals, including notable political and cultural figures.
  • E. Orlando
    Orlando is the middle name of William O. Butler, a 19th-century American military officer and politician.
  • 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_69e2454fc984819088213b58ee87a002 completed April 17, 2026, 2:35 p.m.
NER Named-entity recognition batch_69f1790fbf9c819082ba7b48801a7b39 completed April 29, 2026, 3:20 a.m.
NED1 Entity disambiguation (via context triple) batch_6a0ba799ca948190820308dc1ce11ce3 completed May 18, 2026, 11:58 p.m.
NEDg Description generation batch_6a0ba89950508190a5a94965bce4a899 completed May 19, 2026, 12:02 a.m.
NED2 Entity disambiguation (via description) batch_6a0baa2c5e848190b3f2f99dd4efbfa5 completed May 19, 2026, 12:09 a.m.
Created at: April 17, 2026, 3:19 p.m.