Triple

T10652444
Position Surface form Disambiguated ID Type / Status
Subject Fort Beaufort E251005 entity
Predicate locatedOn P40 FINISHED
Object R63 road
The R63 road is a regional route in South Africa that connects several towns across the Eastern and Western Cape provinces.
E879467 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: R63 road | Statement: [Fort Beaufort, locatedOn, R63 road]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: R63 road
Context triple: [Fort Beaufort, locatedOn, R63 road]
  • A. R66 road
    The R66 road is a regional route in South Africa’s KwaZulu-Natal province that runs through towns such as Ulundi, serving as an important connector between inland communities and other major routes.
  • B. R680 road
    The R680 road is a regional route in Ireland that connects Waterford to Clonmel and other towns in the southeast.
  • C. R566 road
    The R566 road is a regional route in South Africa that connects the township of Ga-Rankuwa with other nearby urban and industrial areas.
  • D. R699 road
    The R699 road is a regional route in County Kilkenny, Ireland, that links the town of Callan with other nearby settlements and the wider Irish road network.
  • E. R106 road
    The R106 road is a regional route in County Dublin, Ireland, linking coastal and suburban areas including the town of Swords.
  • 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: R63 road
Triple: [Fort Beaufort, locatedOn, R63 road]
Generated description
The R63 road is a regional route in South Africa that connects several towns across the Eastern and Western Cape provinces.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07
Target entity: R63 road
Target entity description: The R63 road is a regional route in South Africa that connects several towns across the Eastern and Western Cape provinces.
  • A. R66 road
    The R66 road is a regional route in South Africa’s KwaZulu-Natal province that runs through towns such as Ulundi, serving as an important connector between inland communities and other major routes.
  • B. R680 road
    The R680 road is a regional route in Ireland that connects Waterford to Clonmel and other towns in the southeast.
  • C. R566 road
    The R566 road is a regional route in South Africa that connects the township of Ga-Rankuwa with other nearby urban and industrial areas.
  • D. R699 road
    The R699 road is a regional route in County Kilkenny, Ireland, that links the town of Callan with other nearby settlements and the wider Irish road network.
  • E. R106 road
    The R106 road is a regional route in County Dublin, Ireland, linking coastal and suburban areas including the town of Swords.
  • 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_69d6aa5a4c4881908f39be6efe5981e5 completed April 8, 2026, 7:19 p.m.
NER Named-entity recognition batch_69d6dff78ec88190a4d1863fe87245f6 completed April 8, 2026, 11:08 p.m.
NED1 Entity disambiguation (via context triple) batch_69d98857ec248190bb655d36981a000a completed April 10, 2026, 11:31 p.m.
NEDg Description generation batch_69d98ae8403c81908a229aa06bd0388a completed April 10, 2026, 11:42 p.m.
NED2 Entity disambiguation (via description) batch_69d98ce9ba0c8190a7c62fa670e23705 completed April 10, 2026, 11:51 p.m.
Created at: April 8, 2026, 9:06 p.m.