Triple

T9418268
Position Surface form Disambiguated ID Type / Status
Subject Osip Mandelstam E227083 entity
Predicate notableWork P4 FINISHED
Object Stone
Stone is a landmark early poetry collection by Russian poet Osip Mandelstam, noted for its dense imagery and classical precision.
 E798326 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: Stone | Statement: [Osip Mandelstam, notableWork, Stone]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07 
Target entity: Stone
Context triple: [Osip Mandelstam, notableWork, Stone]
  • A. Stone
    Stone is a market town in Staffordshire, England, known historically for its canal and brewing heritage.
  • B. Stone
    "Stone" is a track by the American rock band Alice in Chains from their album *The Devil Put Dinosaurs Here*.
  • C. Stone
    Stone is a village and civil parish in north-west Kent, England, known for its historic church and proximity to the River Thames and the town of Dartford.
  • D. Stone
    Stone is a common English surname borne by numerous notable individuals across history, including figures in religion, politics, arts, and sciences.
  • E. Stone
    "Stone" is a 2010 American crime drama film directed by John Curran, starring Robert De Niro, Edward Norton, and Milla Jovovich in a tense psychological story of manipulation and redemption.
  • 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: Stone
Triple: [Osip Mandelstam, notableWork, Stone]
Generated description
Stone is a landmark early poetry collection by Russian poet Osip Mandelstam, noted for its dense imagery and classical precision.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07 
Target entity: Stone
Target entity description: Stone is a landmark early poetry collection by Russian poet Osip Mandelstam, noted for its dense imagery and classical precision.
  • A. Stone
    Stone is a common English surname borne by numerous notable individuals across history, including figures in religion, politics, arts, and sciences.
  • B. Stone
    "Stone" is a 2010 American crime drama film directed by John Curran, starring Robert De Niro, Edward Norton, and Milla Jovovich in a tense psychological story of manipulation and redemption.
  • C. Stone
    Stone is a market town in Staffordshire, England, known historically for its canal and brewing heritage.
  • D. Stone
    "Stone" is a track by the American rock band Alice in Chains from their album *The Devil Put Dinosaurs Here*.
  • E. Stone
    Stone is a village and civil parish in north-west Kent, England, known for its historic church and proximity to the River Thames and the town of Dartford.
  • 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_69ca84359e7c819091148ba4b670e436 completed March 30, 2026, 2:09 p.m.
NER Named-entity recognition batch_69cd68cd1e3481909abcb715e2398120 completed April 1, 2026, 6:49 p.m.
NED1 Entity disambiguation (via context triple) batch_69d107c4d73881909ac38781fe90b1da completed April 4, 2026, 12:44 p.m.
NEDg Description generation batch_69d1085a980c8190b4c6d811b07ab180 completed April 4, 2026, 12:47 p.m.
NED2 Entity disambiguation (via description) batch_69d1093f440481909aa27287019191ac completed April 4, 2026, 12:51 p.m.
Created at: March 30, 2026, 7:48 p.m.