Triple

T1179055
Position Surface form Disambiguated ID Type / Status
Subject Falkirk E25093 entity
Predicate hasNearbySite P350 FINISHED
Object Antonine Wall E37094 NE FINISHED

How this triple was built (2 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: Antonine Wall | Statement: [Falkirk, hasNearbySite, Antonine Wall]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Antonine Wall
Context triple: [Falkirk, hasNearbySite, Antonine Wall]
  • A. Antonine Wall chosen
    The Antonine Wall was a Roman frontier fortification in central Scotland marking the northernmost boundary of the Roman Empire in Britain for a brief period in the 2nd century AD.
  • B. Hadrian's Wall
    Hadrian's Wall is a monumental Roman defensive fortification in northern England that marked the empire’s northern frontier in Britain.
  • C. Limes Germanicus
    Limes Germanicus was a fortified frontier system of the Roman Empire that marked and defended its boundary in the regions of Germania.
  • D. Segedunum Roman Fort
    Segedunum Roman Fort is a well-preserved Roman military fort and museum at the eastern end of Hadrian’s Wall in Wallsend, England.
  • E. Theodosian Walls
    The Theodosian Walls are the massive late Roman and Byzantine defensive fortifications that protected Constantinople for over a millennium until its fall in 1453.
  • F. None of above.
  • G. Unsure - the case is ambiguous/there is not enough information to decide.

Provenance (3 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_69a494267b4c819088c97a59182bf56a completed March 1, 2026, 7:31 p.m.
NER Named-entity recognition batch_69a4bd1226fc819083d526ecd22af8ef completed March 1, 2026, 10:26 p.m.
NED1 Entity disambiguation (via context triple) batch_69ac6f1f1c188190a96f5718c4e7d59d completed March 7, 2026, 6:31 p.m.
Created at: March 1, 2026, 7:45 p.m.