Triple

T6762015
Position Surface form Disambiguated ID Type / Status
Subject Salem County E154615 entity
Predicate hasMunicipality P847 FINISHED
Object Woodstown
Woodstown is a small borough located in southwestern New Jersey that serves as a local residential and commercial center within Salem County.
 E617517 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: Woodstown | Statement: [Salem County, hasMunicipality, Woodstown]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07 
Target entity: Woodstown
Context triple: [Salem County, hasMunicipality, Woodstown]
  • A. Gracetown
    Gracetown is a small coastal town in Western Australia known for its beaches, surfing spots, and relaxed seaside atmosphere.
  • B. Parkeston
    Parkeston is a village and port area in Essex, England, situated near Harwich and known historically for its railway and maritime connections.
  • C. Pierpont
    Pierpont is the distinctive middle name of the influential American financier and banker J. P. Morgan.
  • D. Seaford
    Seaford is a coastal town in East Sussex, England, historically notable as a parliamentary borough once represented by prominent figures such as William Pitt the Elder.
  • E. Wyandanch
    Wyandanch is a hamlet in the town of Babylon in Suffolk County, New York, located on Long Island.
  • 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: Woodstown
Triple: [Salem County, hasMunicipality, Woodstown]
Generated description
Woodstown is a small borough located in southwestern New Jersey that serves as a local residential and commercial center within Salem County.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07 
Target entity: Woodstown
Target entity description: Woodstown is a small borough located in southwestern New Jersey that serves as a local residential and commercial center within Salem County.
  • A. Gracetown
    Gracetown is a small coastal town in Western Australia known for its beaches, surfing spots, and relaxed seaside atmosphere.
  • B. Parkeston
    Parkeston is a village and port area in Essex, England, situated near Harwich and known historically for its railway and maritime connections.
  • C. Pierpont
    Pierpont is the distinctive middle name of the influential American financier and banker J. P. Morgan.
  • D. Seaford
    Seaford is a coastal town in East Sussex, England, historically notable as a parliamentary borough once represented by prominent figures such as William Pitt the Elder.
  • E. Wyandanch
    Wyandanch is a hamlet in the town of Babylon in Suffolk County, New York, located on Long Island.
  • 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_69c688109c1c8190added9a221292af0 completed March 27, 2026, 1:37 p.m.
NER Named-entity recognition batch_69c6d21444dc8190a290af86c81e96a5 completed March 27, 2026, 6:53 p.m.
NED1 Entity disambiguation (via context triple) batch_69c712b352d08190932bc99dd3d673ba completed March 27, 2026, 11:28 p.m.
NEDg Description generation batch_69c713842b9c8190ae31eba0bd449968 completed March 27, 2026, 11:32 p.m.
NED2 Entity disambiguation (via description) batch_69c71444e9ec8190a68531ed29fd9377 completed March 27, 2026, 11:35 p.m.
Created at: March 27, 2026, 2:12 p.m.