Triple

T30160231
Position Surface form Disambiguated ID Type / Status
Subject Queenborough Castle site E766643 entity
Predicate hasFormerSiteOf P4380 FINISHED
Object Queenborough Castle
Queenborough Castle was a 14th-century royal fortress on the Isle of Sheppey in Kent, England, notable for its unique concentric design and role in defending the Thames estuary.
E1904731 NE FINISHED

How this triple was built (3 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: Queenborough Castle | Statement: [Queenborough Castle site, hasFormerSiteOf, Queenborough Castle]
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: Queenborough Castle
Triple: [Queenborough Castle site, hasFormerSiteOf, Queenborough Castle]
Generated description
Queenborough Castle was a 14th-century royal fortress on the Isle of Sheppey in Kent, England, notable for its unique concentric design and role in defending the Thames estuary.
PD Predicate disambiguation gpt-5-mini-2025-08-07
Target predicate: hasFormerSiteOf
Context triple: [Queenborough Castle site, hasFormerSiteOf, Queenborough Castle]
  • A. formerSiteOf chosen
    Indicates that a location previously hosted or contained something (such as a structure, organization, or event) that is no longer present there.
  • B. isNowSiteOf
    Indicates that a location currently occupies or serves as the site where another place, structure, or entity once existed or was situated.
  • C. overlooksFormerSiteOf
    Indicates that one location has a view toward or looks out over the place where another location or structure used to exist.
  • D. formerMunicipalityOf
    Indicates that an entity was previously an independent municipality that has since been merged into or replaced by the referenced municipality.
  • E. formerlyLocatedOn
    Indicates that an entity was once located on or situated upon another entity, but is no longer in that position.
  • F. None of above.

Provenance (6 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_69f2247a968881909d79c18f2bfcb275 completed April 29, 2026, 3:32 p.m.
NER Named-entity recognition batch_69fcda3699948190adb57625bae08091 completed May 7, 2026, 6:30 p.m.
NED1 Entity disambiguation (via context triple) batch_6a276431ce1c8190b8b0a01de38cb795 completed June 9, 2026, 12:54 a.m.
NEDg Description generation batch_6a2764c1f1088190867daed1b6e14d5d completed June 9, 2026, 12:56 a.m.
NED2 Entity disambiguation (via description) batch_6a27653358bc8190891d1b1b80f9be87 completed June 9, 2026, 12:58 a.m.
PD Predicate disambiguation batch_69fcd8fd16d08190b0aca6e19a632e99 completed May 7, 2026, 6:25 p.m.
Created at: April 29, 2026, 7:21 p.m.