Triple

T13531827
Position Surface form Disambiguated ID Type / Status
Subject Woodlands, Singapore E323149 entity
Predicate hasRoad P959 FINISHED
Object Marsiling Lane
Marsiling Lane is a local road situated in the residential town of Woodlands in northern Singapore.
E1051836 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: Marsiling Lane | Statement: [Woodlands, Singapore, hasRoad, Marsiling Lane]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Marsiling Lane
Context triple: [Woodlands, Singapore, hasRoad, Marsiling Lane]
  • A. Muroor Road
    Muroor Road is a major arterial roadway in Abu Dhabi that runs through the city and connects key residential and commercial districts on Abu Dhabi Island.
  • B. Werong Road
    Werong Road is a rural access road in New South Wales, Australia, that serves the Mount Werong area within the Central Tablelands region.
  • C. Bras Basah Road
    Bras Basah Road is a major thoroughfare in Singapore’s civic and cultural district, lined with museums, educational institutions, and historic landmarks.
  • D. Sha Tau Kok Road
    Sha Tau Kok Road is a major roadway in Hong Kong’s New Territories that connects the town of Fanling to the border area of Sha Tau Kok.
  • E. Keppel Road
    Keppel Road is a major thoroughfare in Singapore that connects the central business district to the southern waterfront and port areas.
  • 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: Marsiling Lane
Triple: [Woodlands, Singapore, hasRoad, Marsiling Lane]
Generated description
Marsiling Lane is a local road situated in the residential town of Woodlands in northern Singapore.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07
Target entity: Marsiling Lane
Target entity description: Marsiling Lane is a local road situated in the residential town of Woodlands in northern Singapore.
  • A. Muroor Road
    Muroor Road is a major arterial roadway in Abu Dhabi that runs through the city and connects key residential and commercial districts on Abu Dhabi Island.
  • B. Werong Road
    Werong Road is a rural access road in New South Wales, Australia, that serves the Mount Werong area within the Central Tablelands region.
  • C. Bras Basah Road
    Bras Basah Road is a major thoroughfare in Singapore’s civic and cultural district, lined with museums, educational institutions, and historic landmarks.
  • D. Sha Tau Kok Road
    Sha Tau Kok Road is a major roadway in Hong Kong’s New Territories that connects the town of Fanling to the border area of Sha Tau Kok.
  • E. Keppel Road
    Keppel Road is a major thoroughfare in Singapore that connects the central business district to the southern waterfront and port areas.
  • 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_69d80766a21881909f21a1b7421d3b8a completed April 9, 2026, 8:09 p.m.
NER Named-entity recognition batch_69dbafbb34548190a6b44faa48125cd4 completed April 12, 2026, 2:44 p.m.
NED1 Entity disambiguation (via context triple) batch_69f77f84935c8190b9e41f44140066e5 completed May 3, 2026, 5:01 p.m.
NEDg Description generation batch_69f783e6f670819082fe29673a47ed1e completed May 3, 2026, 5:20 p.m.
NED2 Entity disambiguation (via description) batch_69f7849416b88190a0ef9d3e26e7b129 completed May 3, 2026, 5:23 p.m.
Created at: April 9, 2026, 9:44 p.m.