Triple

T3435335
Position Surface form Disambiguated ID Type / Status
Subject Locris E72437 entity
Predicate hasCity P316 FINISHED
Object Opus
Opus was the chief city of the ancient Greek region of Eastern Locris, known as Opuntian Locris.
E357568 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: Opus | Statement: [Locris, hasCity, Opus]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Opus
Context triple: [Locris, hasCity, Opus]
  • A. Opus 200
    Opus 200 is a non-fiction collection by Isaac Asimov that surveys and reflects on his extensive body of work up to his 200th published book.
  • B. Opera Posthuma
    Opera Posthuma is the posthumously published collection of Baruch Spinoza’s major philosophical writings, including his seminal work Ethics.
  • C. Opus 100
    Opus 100 is a commemorative collection by Isaac Asimov that showcases excerpts and essays from his first hundred published books, reflecting the breadth of his work in science fiction and popular science.
  • D. Opus 100
    Opus 100 is the concert pipe organ installed in the Morton H. Meyerson Symphony Center in Dallas, renowned for its rich tonal palette and architectural integration with the hall.
  • E. Rhapsody
    Rhapsody was Apple’s early post-NeXT operating system project that combined NeXTSTEP’s advanced technologies with a Mac OS–compatible environment, serving as a key transitional step toward what became Mac OS X.
  • 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: Opus
Triple: [Locris, hasCity, Opus]
Generated description
Opus was the chief city of the ancient Greek region of Eastern Locris, known as Opuntian Locris.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07
Target entity: Opus
Target entity description: Opus was the chief city of the ancient Greek region of Eastern Locris, known as Opuntian Locris.
  • A. Opus 200
    Opus 200 is a non-fiction collection by Isaac Asimov that surveys and reflects on his extensive body of work up to his 200th published book.
  • B. Opera Posthuma
    Opera Posthuma is the posthumously published collection of Baruch Spinoza’s major philosophical writings, including his seminal work Ethics.
  • C. Opus 100
    Opus 100 is a commemorative collection by Isaac Asimov that showcases excerpts and essays from his first hundred published books, reflecting the breadth of his work in science fiction and popular science.
  • D. Opus 100
    Opus 100 is the concert pipe organ installed in the Morton H. Meyerson Symphony Center in Dallas, renowned for its rich tonal palette and architectural integration with the hall.
  • E. Rhapsody
    Rhapsody was Apple’s early post-NeXT operating system project that combined NeXTSTEP’s advanced technologies with a Mac OS–compatible environment, serving as a key transitional step toward what became Mac OS X.
  • 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_69ad85af50288190a854b76653deee6f completed March 8, 2026, 2:20 p.m.
NER Named-entity recognition batch_69adb9c3300881909f5c3544f8923b41 completed March 8, 2026, 6:02 p.m.
NED1 Entity disambiguation (via context triple) batch_69b3547fd15481909c310b731231d5bb completed March 13, 2026, 12:04 a.m.
NEDg Description generation batch_69b3588a03c08190aaed9a22837f2c0d completed March 13, 2026, 12:21 a.m.
NED2 Entity disambiguation (via description) batch_69b358e305548190b861e5ecbb59fa56 completed March 13, 2026, 12:22 a.m.
Created at: March 8, 2026, 3:16 p.m.