Triple

T14029686
Position Surface form Disambiguated ID Type / Status
Subject Athlone E337553 entity
Predicate hasLandmark P105 FINISHED
Object Hazendal
Hazendal is a residential suburb of Cape Town, South Africa, situated near Athlone on the Cape Flats.
E1074894 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: Hazendal | Statement: [Athlone, hasLandmark, Hazendal]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Hazendal
Context triple: [Athlone, hasLandmark, Hazendal]
  • A. Harksheide
    Harksheide was a former municipality in Schleswig-Holstein, Germany, that later became part of the city of Norderstedt.
  • B. Hackenholt
    Hackenholt is a German surname most notably associated with Lorenz Hackenholt, an SS officer involved in the Nazi extermination camps during World War II.
  • C. Herkinge
    Herkinge is a small settlement located in the Dutch province of South Holland.
  • D. Wildervank
    Wildervank is a village in the Dutch province of Groningen, known historically for its peat colonies and canal-side settlement pattern.
  • E. Velburg
    Velburg is a small Bavarian town in southeastern Germany known for its historic castle ruins and scenic location in the Upper Palatinate region.
  • 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: Hazendal
Triple: [Athlone, hasLandmark, Hazendal]
Generated description
Hazendal is a residential suburb of Cape Town, South Africa, situated near Athlone on the Cape Flats.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07
Target entity: Hazendal
Target entity description: Hazendal is a residential suburb of Cape Town, South Africa, situated near Athlone on the Cape Flats.
  • A. Harksheide
    Harksheide was a former municipality in Schleswig-Holstein, Germany, that later became part of the city of Norderstedt.
  • B. Hackenholt
    Hackenholt is a German surname most notably associated with Lorenz Hackenholt, an SS officer involved in the Nazi extermination camps during World War II.
  • C. Herkinge
    Herkinge is a small settlement located in the Dutch province of South Holland.
  • D. Wildervank
    Wildervank is a village in the Dutch province of Groningen, known historically for its peat colonies and canal-side settlement pattern.
  • E. Velburg
    Velburg is a small Bavarian town in southeastern Germany known for its historic castle ruins and scenic location in the Upper Palatinate region.
  • 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_69d81c6543a48190bd5ba93d7419e797 completed April 9, 2026, 9:38 p.m.
NER Named-entity recognition batch_69de2fa9f8248190930954d609dee5f1 completed April 14, 2026, 12:14 p.m.
NED1 Entity disambiguation (via context triple) batch_69fbc335a474819084c310b10e0ded9a completed May 6, 2026, 10:39 p.m.
NEDg Description generation batch_69fbc51585608190817e9a80666b7740 completed May 6, 2026, 10:47 p.m.
NED2 Entity disambiguation (via description) batch_69fbc57bf4188190aace2c976d842b43 completed May 6, 2026, 10:49 p.m.
Created at: April 9, 2026, 10:20 p.m.