Triple

T1498900
Position Surface form Disambiguated ID Type / Status
Subject Saint Peter Port E29749 entity
Predicate hasLandmark P105 FINISHED
Object Castle Cornet
Castle Cornet is a historic coastal fortress and former royal castle guarding the harbor of Saint Peter Port on the island of Guernsey.
E170372 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: Castle Cornet | Statement: [Saint Peter Port, hasLandmark, Castle Cornet]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Castle Cornet
Context triple: [Saint Peter Port, hasLandmark, Castle Cornet]
  • A. Bower’s Tower
    Bower’s Tower is a historic stone watchtower and popular tourist viewpoint in Ibadan, Nigeria, offering panoramic views of the city.
  • B. Lady’s Tower
    Lady’s Tower is a historic 18th-century coastal lookout and bathing tower near Elie in Fife, Scotland, known for its dramatic clifftop setting and sea views.
  • C. Red Castle
    Red Castle is a ruined medieval fortress overlooking Lunan Bay on the east coast of Scotland.
  • D. Playstead
    Playstead is a large recreational area within Boston’s Franklin Park, featuring open fields and facilities for sports and community activities.
  • E. Beauchamp Tower
    Beauchamp Tower is a historic medieval tower within the Tower of London complex, best known for its use as a prison and for the extensive prisoner graffiti carved into its walls.
  • 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: Castle Cornet
Triple: [Saint Peter Port, hasLandmark, Castle Cornet]
Generated description
Castle Cornet is a historic coastal fortress and former royal castle guarding the harbor of Saint Peter Port on the island of Guernsey.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07
Target entity: Castle Cornet
Target entity description: Castle Cornet is a historic coastal fortress and former royal castle guarding the harbor of Saint Peter Port on the island of Guernsey.
  • A. Bower’s Tower
    Bower’s Tower is a historic stone watchtower and popular tourist viewpoint in Ibadan, Nigeria, offering panoramic views of the city.
  • B. Lady’s Tower
    Lady’s Tower is a historic 18th-century coastal lookout and bathing tower near Elie in Fife, Scotland, known for its dramatic clifftop setting and sea views.
  • C. Red Castle
    Red Castle is a ruined medieval fortress overlooking Lunan Bay on the east coast of Scotland.
  • D. Playstead
    Playstead is a large recreational area within Boston’s Franklin Park, featuring open fields and facilities for sports and community activities.
  • E. Beauchamp Tower
    Beauchamp Tower is a historic medieval tower within the Tower of London complex, best known for its use as a prison and for the extensive prisoner graffiti carved into its walls.
  • 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_69a498dba1d8819093b46a3a8d2485f1 completed March 1, 2026, 7:51 p.m.
NER Named-entity recognition batch_69a4c6f0ce988190aafab4a6e0dfd710 completed March 1, 2026, 11:08 p.m.
NED1 Entity disambiguation (via context triple) batch_69ad1cb19b708190a28b1a0037860202 completed March 8, 2026, 6:52 a.m.
NEDg Description generation batch_69ad1db1c6008190bbe61bad1a2a7e72 completed March 8, 2026, 6:56 a.m.
NED2 Entity disambiguation (via description) batch_69ad1e1e9fa081909201036f686fa110 completed March 8, 2026, 6:58 a.m.
Created at: March 1, 2026, 8:12 p.m.