Triple

T32405730
Position Surface form Disambiguated ID Type / Status
Subject Green Line A branch E828072 entity
Predicate formerServiceTo P43939 FINISHED
Object Watertown
Watertown is a city in Massachusetts located just west of Boston, known for its residential neighborhoods, historic Armenian community, and proximity to the Charles River.
 E2288039 NE FINISHED

How this triple was built (3 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: Watertown | Statement: [Green Line A branch, formerServiceTo, Watertown]
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: Watertown
Triple: [Green Line A branch, formerServiceTo, Watertown]
Generated description
Watertown is a city in Massachusetts located just west of Boston, known for its residential neighborhoods, historic Armenian community, and proximity to the Charles River.
PD Predicate disambiguation gpt-5-mini-2025-08-07 
Target predicate: formerServiceTo
Context triple: [Green Line A branch, formerServiceTo, Watertown]
  • A. formerServicePattern chosen
    Indicates that an entity previously provided a particular service or operated under a specific service pattern, but no longer does so.
  • B. formerFunction
    Indicates that an entity previously held a specific role, position, or function but no longer does so.
  • C. formerTransport
    Indicates that an entity previously served as a means of transportation for another entity but no longer does so.
  • D. formerCustom
    Indicates that one entity was previously a customer of another entity but is no longer in that role.
  • E. formerField
    Indicates that an entity previously had a particular field, role, or area of activity, but no longer does.
  • F. None of above.

Provenance (6 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_69f34919342c8190a4c3bf35a90d4e58 completed April 30, 2026, 12:20 p.m.
NER Named-entity recognition batch_69ff7bc112088190851501fb2a16103d completed May 9, 2026, 6:24 p.m.
NED1 Entity disambiguation (via context triple) batch_6a5a5d8b1b2c8190be4d03af0cf54b51 completed July 17, 2026, 4:51 p.m.
NEDg Description generation batch_6a5a5ede143c8190b950f1b56bbd9df0 completed July 17, 2026, 4:57 p.m.
NED2 Entity disambiguation (via description) batch_6a5a5f44a25c81909beb4bc401446304 completed July 17, 2026, 4:58 p.m.
PD Predicate disambiguation batch_69ff7b45507c81909753866ad733601a completed May 9, 2026, 6:21 p.m.
Created at: May 1, 2026, 12:53 a.m.