Triple

T38457
Position Surface form Disambiguated ID Type / Status
Subject MBTA Red Line E761 entity
Predicate servesStation P839 FINISHED
Object Andrew
Andrew is a subway station in South Boston on the Massachusetts Bay Transportation Authority's Red Line.
 E18412 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: Andrew | Statement: [MBTA Red Line, servesStation, Andrew]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07 
Target entity: Andrew
Context triple: [MBTA Red Line, servesStation, Andrew]
  • A. Andrew
    Andrew is a masculine given name of Greek origin meaning "manly" or "brave," widely used in English-speaking countries and beyond.
  • B. Stephen
    Stephen is the middle name of Harold Stephen Black, an American electrical engineer known for inventing the negative feedback amplifier.
  • C. John
    John H. Sununu is an American politician and engineer who served as Governor of New Hampshire and later as White House Chief of Staff under President George H. W. Bush.
  • D. James
    James is a common masculine given name of Hebrew origin meaning "supplanter," widely used in English-speaking countries.
  • E. Gavin
    Gavin is a masculine given name of Celtic origin, commonly used in English-speaking countries.
  • 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: Andrew
Triple: [MBTA Red Line, servesStation, Andrew]
Generated description
Andrew is a subway station in South Boston on the Massachusetts Bay Transportation Authority's Red Line.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07 
Target entity: Andrew
Target entity description: Andrew is a subway station in South Boston on the Massachusetts Bay Transportation Authority's Red Line.
  • A. Andrew
    Andrew is a masculine given name of Greek origin meaning "manly" or "brave," widely used in English-speaking countries and beyond.
  • B. Stephen
    Stephen is the middle name of Harold Stephen Black, an American electrical engineer known for inventing the negative feedback amplifier.
  • C. John
    John H. Sununu is an American politician and engineer who served as Governor of New Hampshire and later as White House Chief of Staff under President George H. W. Bush.
  • D. James
    James is a common masculine given name of Hebrew origin meaning "supplanter," widely used in English-speaking countries.
  • E. Gavin
    Gavin is a masculine given name of Celtic origin, commonly used in English-speaking countries.
  • 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_69a247a8f6c08190bac804906d62ed5a completed Feb. 28, 2026, 1:40 a.m.
NER Named-entity recognition batch_69a24ec1ef5481909daf99654dfa3f57 completed Feb. 28, 2026, 2:11 a.m.
NED1 Entity disambiguation (via context triple) batch_69a2c93548988190a7514e0cc2df0de4 completed Feb. 28, 2026, 10:53 a.m.
NEDg Description generation batch_69a2c9b112288190b081ef6ca567e594 completed Feb. 28, 2026, 10:55 a.m.
NED2 Entity disambiguation (via description) batch_69a2ca31ebd4819082c59d25a46f872d completed Feb. 28, 2026, 10:57 a.m.
Created at: Feb. 28, 2026, 1:46 a.m.