Triple

T1068636
Position Surface form Disambiguated ID Type / Status
Subject John Howland E23272 entity
Predicate spouse P13 FINISHED
Object Elizabeth Tilley
Elizabeth Tilley was a Mayflower passenger who survived the first harsh years at Plymouth Colony and later married fellow colonist John Howland, becoming an important ancestor of many notable Americans.
 E202948 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: Elizabeth Tilley | Statement: [John Howland, spouse, Elizabeth Tilley]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07 
Target entity: Elizabeth Tilley
Context triple: [John Howland, spouse, Elizabeth Tilley]
  • A. Tiana Rogers
    Tiana Rogers was a Cherokee woman known for her marriage to Sam Houston, the American statesman and leader of the Republic of Texas.
  • B. Sarah Thorne
    Sarah Thorne was the wife of Leonard Darwin, son of the naturalist Charles Darwin.
  • C. Tabitha Grant
    Tabitha Grant is the daughter of British actor Hugh Grant and his former partner Tinglan Hong.
  • D. Lindsay Roy
    Lindsay Roy is a Scottish Labour politician and former Member of Parliament who represented the Glenrothes constituency in the UK Parliament.
  • E. Josie Lloyd
    Josie Lloyd is an American actress known for her television work in the 1960s, including appearances on shows like "The Andy Griffith Show."
  • 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: Elizabeth Tilley
Triple: [John Howland, spouse, Elizabeth Tilley]
Generated description
Elizabeth Tilley was a Mayflower passenger who survived the first harsh years at Plymouth Colony and later married fellow colonist John Howland, becoming an important ancestor of many notable Americans.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07 
Target entity: Elizabeth Tilley
Target entity description: Elizabeth Tilley was a Mayflower passenger who survived the first harsh years at Plymouth Colony and later married fellow colonist John Howland, becoming an important ancestor of many notable Americans.
  • A. Tiana Rogers
    Tiana Rogers was a Cherokee woman known for her marriage to Sam Houston, the American statesman and leader of the Republic of Texas.
  • B. Sarah Thorne
    Sarah Thorne was the wife of Leonard Darwin, son of the naturalist Charles Darwin.
  • C. Tabitha Grant
    Tabitha Grant is the daughter of British actor Hugh Grant and his former partner Tinglan Hong.
  • D. Lindsay Roy
    Lindsay Roy is a Scottish Labour politician and former Member of Parliament who represented the Glenrothes constituency in the UK Parliament.
  • E. Josie Lloyd
    Josie Lloyd is an American actress known for her television work in the 1960s, including appearances on shows like "The Andy Griffith Show."
  • 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_69a493ee1f908190992b5f0d1b04459b completed March 1, 2026, 7:30 p.m.
NER Named-entity recognition batch_69a4b91389888190b4b96d7ee4dda206 completed March 1, 2026, 10:09 p.m.
NED1 Entity disambiguation (via context triple) batch_69adbf33c7808190962fb6c2496b4ec7 completed March 8, 2026, 6:25 p.m.
NEDg Description generation batch_69adbff135188190908058a2e2d41a1e completed March 8, 2026, 6:29 p.m.
NED2 Entity disambiguation (via description) batch_69adc0832cd881909702f380412702d5 completed March 8, 2026, 6:31 p.m.
Created at: March 1, 2026, 7:42 p.m.