Triple

T19981630
Position Surface form Disambiguated ID Type / Status
Subject Adam E493828 entity
Predicate employer P7 FINISHED
Object Orlando de Boys
Orlando de Boys is a fictional young nobleman and one of the central characters in William Shakespeare’s comedy "As You Like It."
 E1403716 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 de Boys | Statement: [Adam, employer, Orlando de Boys]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07 
Target entity: Orlando de Boys
Context triple: [Adam, employer, Orlando de Boys]
  • A. Orlando de Boys
    Orlando de Boys is a central character in Shakespeare's comedy "As You Like It," known as the younger, mistreated brother who falls in love with Rosalind.
  • B. Anthony Boys
    Anthony Boys is a film editor best known for his work on the political satire film "In the Loop."
  • C. Henry Borrell
    Henry Borrell was a clockmaker associated with the timekeeping installations of St. Michael's Church.
  • D. Orlando Lorenzini
    Orlando Lorenzini was an Italian military officer best known for commanding Axis forces during the World War II Battle of Sidi Bou Zid in Tunisia.
  • E. Daniel Orlandi
    Daniel Orlandi is an American costume designer known for his stylish, period-accurate work on films such as "Down with Love" and numerous collaborations with director Peyton Reed.
  • 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 de Boys
Triple: [Adam, employer, Orlando de Boys]
Generated description
Orlando de Boys is a fictional young nobleman and one of the central characters in William Shakespeare’s comedy "As You Like It."
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07 
Target entity: Orlando de Boys
Target entity description: Orlando de Boys is a fictional young nobleman and one of the central characters in William Shakespeare’s comedy "As You Like It."
  • A. Orlando de Boys chosen
    Orlando de Boys is a central character in Shakespeare's comedy "As You Like It," known as the younger, mistreated brother who falls in love with Rosalind.
  • B. Anthony Boys
    Anthony Boys is a film editor best known for his work on the political satire film "In the Loop."
  • C. Henry Borrell
    Henry Borrell was a clockmaker associated with the timekeeping installations of St. Michael's Church.
  • D. Orlando Lorenzini
    Orlando Lorenzini was an Italian military officer best known for commanding Axis forces during the World War II Battle of Sidi Bou Zid in Tunisia.
  • E. Daniel Orlandi
    Daniel Orlandi is an American costume designer known for his stylish, period-accurate work on films such as "Down with Love" and numerous collaborations with director Peyton Reed.
  • F. None of above.

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_69da626a67648190af9653832a3aeced completed April 11, 2026, 3:02 p.m.
NER Named-entity recognition batch_69e65d13a8a88190bf5f4f697793f4c9 completed April 20, 2026, 5:06 p.m.
NED1 Entity disambiguation (via context triple) batch_6a0804fb67ac819083a9dd9c11651acd completed May 16, 2026, 5:47 a.m.
NEDg Description generation batch_6a0806fe43148190820bc3246c6697db completed May 16, 2026, 5:56 a.m.
NED2 Entity disambiguation (via description) batch_6a08075f1a48819082f217db39841fdb completed May 16, 2026, 5:57 a.m.
Created at: April 11, 2026, 3:28 p.m.