Triple

T17345728
Position Surface form Disambiguated ID Type / Status
Subject Robert Lugar E421682 entity
Predicate notableWork P4 FINISHED
Object Denham Mount NE ONDG

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: Denham Mount | Statement: [Robert Lugar, notableWork, Denham Mount]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Denham Mount
Context triple: [Robert Lugar, notableWork, Denham Mount]
  • A. Hanham Mount
    Hanham Mount is a historic hilltop site in Hanham, England, known as a notable local landmark and viewpoint.
  • B. Forbury Hill
    Forbury Hill is a historic earthwork mound in Reading, England, forming part of the Forbury Gardens near the ruins of Reading Abbey and long associated with medieval defensive and ceremonial uses.
  • C. Dunstable Downs
    Dunstable Downs is a chalk escarpment in Bedfordshire, England, known for its scenic views, wildlife, and popularity for walking and kite flying.
  • D. Wotton Hill
    Wotton Hill is a prominent hill and viewpoint near Wotton-under-Edge in Gloucestershire, England, known for its scenic walks and traditional May Day celebrations.
  • E. Lewesdon Hill
    Lewesdon Hill is a prominent, wooded hill in southwest England that forms the highest natural point in the county of Dorset.
  • 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: Denham Mount
Triple: [Robert Lugar, notableWork, Denham Mount]
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07
Target entity: Denham Mount
Target entity description: Denham Mount is a historic country house in Denham, Buckinghamshire, England, designed in the early 19th century by architect Robert Lugar.
  • A. Hanham Mount
    Hanham Mount is a historic hilltop site in Hanham, England, known as a notable local landmark and viewpoint.
  • B. Forbury Hill
    Forbury Hill is a historic earthwork mound in Reading, England, forming part of the Forbury Gardens near the ruins of Reading Abbey and long associated with medieval defensive and ceremonial uses.
  • C. Dunstable Downs
    Dunstable Downs is a chalk escarpment in Bedfordshire, England, known for its scenic views, wildlife, and popularity for walking and kite flying.
  • D. Wotton Hill
    Wotton Hill is a prominent hill and viewpoint near Wotton-under-Edge in Gloucestershire, England, known for its scenic walks and traditional May Day celebrations.
  • E. Lewesdon Hill
    Lewesdon Hill is a prominent, wooded hill in southwest England that forms the highest natural point in the county of Dorset.
  • F. None of above. chosen

Provenance (4 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_69d889d520008190a26917a95bf1c2ea completed April 10, 2026, 5:25 a.m.
NER Named-entity recognition batch_69e43a286d34819080c5148c220fd5a1 completed April 19, 2026, 2:12 a.m.
NED1 Entity disambiguation (via context triple) batch_6a0195546198819085804ec0b5b18040 completed May 11, 2026, 8:37 a.m.
NEDg Description generation batch_6a01965807cc819088792a88b8a099d3 in_progress May 11, 2026, 8:42 a.m.
Created at: April 10, 2026, 5:44 a.m.