Triple

T7222503
Position Surface form Disambiguated ID Type / Status
Subject George Swanson Starling E150292 entity
Predicate familyName P18 FINISHED
Object Starling
Starling is a surname of English origin borne by various notable individuals across fields such as science, politics, and the arts.
E649568 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: Starling | Statement: [George Swanson Starling, familyName, Starling]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Starling
Context triple: [George Swanson Starling, familyName, Starling]
  • A. Pidgeon
    Pidgeon is a surname most notably associated with Canadian-American actor Walter Pidgeon, a prominent film star of Hollywood’s classic era.
  • B. Sparrow
    Sparrow is a recurring character in Alison Bechdel’s long-running comic strip "Dykes to Watch Out For," known for her involvement in the strip’s interconnected lesbian and queer community.
  • C. Vogel
    Vogel is a German-origin surname borne by numerous individuals, including figures in sports, arts, science, and public life.
  • D. Vogel
    Vogel is a prominent mountain and ski resort in the Julian Alps of Slovenia, overlooking Lake Bohinj and popular for hiking, skiing, and panoramic views.
  • E. Martlets
    Martlets is the name of McGill University's women's varsity sports teams, known for their strong athletic tradition in Canadian university sports.
  • 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: Starling
Triple: [George Swanson Starling, familyName, Starling]
Generated description
Starling is a surname of English origin borne by various notable individuals across fields such as science, politics, and the arts.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07
Target entity: Starling
Target entity description: Starling is a surname of English origin borne by various notable individuals across fields such as science, politics, and the arts.
  • A. Pidgeon
    Pidgeon is a surname most notably associated with Canadian-American actor Walter Pidgeon, a prominent film star of Hollywood’s classic era.
  • B. Sparrow
    Sparrow is a recurring character in Alison Bechdel’s long-running comic strip "Dykes to Watch Out For," known for her involvement in the strip’s interconnected lesbian and queer community.
  • C. Vogel
    Vogel is a German-origin surname borne by numerous individuals, including figures in sports, arts, science, and public life.
  • D. Vogel
    Vogel is a prominent mountain and ski resort in the Julian Alps of Slovenia, overlooking Lake Bohinj and popular for hiking, skiing, and panoramic views.
  • E. Martlets
    Martlets is the name of McGill University's women's varsity sports teams, known for their strong athletic tradition in Canadian university sports.
  • 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_69c687effb44819092b95d07d0368c9f completed March 27, 2026, 1:36 p.m.
NER Named-entity recognition batch_69c6e9b42c5c81908c405f161c35ffb4 completed March 27, 2026, 8:33 p.m.
NED1 Entity disambiguation (via context triple) batch_69c7cc0c3ff08190b855fa57967586ce completed March 28, 2026, 12:39 p.m.
NEDg Description generation batch_69c7cc93801081908c9617bc0f768bd3 completed March 28, 2026, 12:41 p.m.
NED2 Entity disambiguation (via description) batch_69c7cd337e14819089af22ff14a8dcf4 completed March 28, 2026, 12:44 p.m.
Created at: March 27, 2026, 2:54 p.m.