Triple

T32098683
Position Surface form Disambiguated ID Type / Status
Subject Twechar E819786 entity
Predicate hasNearbyRomanFort P165592 FINISHED
Object Bar Hill Roman fort
Bar Hill Roman fort is a Roman military fortification on the Antonine Wall in central Scotland, notable for its well-preserved remains and archaeological finds.
 E1991508 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: Bar Hill Roman fort | Statement: [Twechar, hasNearbyRomanFort, Bar Hill Roman fort]
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: Bar Hill Roman fort
Triple: [Twechar, hasNearbyRomanFort, Bar Hill Roman fort]
Generated description
Bar Hill Roman fort is a Roman military fortification on the Antonine Wall in central Scotland, notable for its well-preserved remains and archaeological finds.
PD Predicate disambiguation gpt-5-mini-2025-08-07 
Target predicate: hasNearbyRomanFort
Context triple: [Twechar, hasNearbyRomanFort, Bar Hill Roman fort]
  • A. nearRomanFort chosen
    Indicates that one entity is located close to a Roman fort.
  • B. nearbyRomanTown
    Indicates that one location is geographically close to a town that existed during the Roman period.
  • C. wasRomanFort
    Indicates that the subject functioned as a Roman military fort at some point in time.
  • D. hasFortificationNearby
    Indicates that one entity is located in proximity to, or within the immediate area of, a fortification structure associated with it.
  • E. hasRomanRemains
    Indicates that the subject contains or is the location of physical remains or archaeological evidence from the Roman period.
  • 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_69f34901106881908ea893ad504a08be completed April 30, 2026, 12:20 p.m.
NER Named-entity recognition batch_69ff246e0d4481908bcec718e1d4025b completed May 9, 2026, 12:11 p.m.
NED1 Entity disambiguation (via context triple) batch_6a2eddfb63ec8190954934893a141878 completed June 14, 2026, 4:59 p.m.
NEDg Description generation batch_6a2edf10d3e08190ba2869891314532a completed June 14, 2026, 5:04 p.m.
NED2 Entity disambiguation (via description) batch_6a2ee07c3fd8819087148aa1c1ca6c43 completed June 14, 2026, 5:10 p.m.
PD Predicate disambiguation batch_69ff23cb70ac81909b776ace4597ae9c completed May 9, 2026, 12:08 p.m.
Created at: May 1, 2026, 12:26 a.m.