Triple
T11011502
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | John Neville |
E260257
|
entity |
| Predicate | spouse |
P13
|
FINISHED |
| Object |
Caroline Hopper
Caroline Hopper is known as the spouse of English actor and theatre director John Neville.
|
E930307
|
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: Caroline Hopper | Statement: [John Neville, spouse, Caroline Hopper]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Caroline Hopper Context triple: [John Neville, spouse, Caroline Hopper]
-
A.
Caroline Severance
Caroline Severance was a prominent 19th-century American suffragist, abolitionist, and social reformer often called the "Mother of Clubs" for her pioneering role in the women's club movement.
-
B.
Caroline Dana Blymyer
Caroline Dana Blymyer was the wife of Charles G. Dawes, the 30th Vice President of the United States and Nobel Peace Prize–winning statesman.
-
C.
Marguerite Harrison
Marguerite Harrison was an American journalist and spy known for her intelligence work in post–World War I Europe and the Soviet Union.
-
D.
Marguerite Harrison
Marguerite Harrison is an American documentary filmmaker best known for directing the 1999 film "Grass," which explores the history of marijuana prohibition in the United States.
-
E.
Peggy Harper
Peggy Harper is best known as the former wife of American singer-songwriter Paul Simon.
- 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: Caroline Hopper Triple: [John Neville, spouse, Caroline Hopper]
Generated description
Caroline Hopper is known as the spouse of English actor and theatre director John Neville.
NED2
Entity disambiguation (via description)
gpt-5-mini-2025-08-07
Target entity: Caroline Hopper Target entity description: Caroline Hopper is known as the spouse of English actor and theatre director John Neville.
-
A.
Caroline Severance
Caroline Severance was a prominent 19th-century American suffragist, abolitionist, and social reformer often called the "Mother of Clubs" for her pioneering role in the women's club movement.
-
B.
Caroline Dana Blymyer
Caroline Dana Blymyer was the wife of Charles G. Dawes, the 30th Vice President of the United States and Nobel Peace Prize–winning statesman.
-
C.
Marguerite Harrison
Marguerite Harrison was an American journalist and spy known for her intelligence work in post–World War I Europe and the Soviet Union.
-
D.
Marguerite Harrison
Marguerite Harrison is an American documentary filmmaker best known for directing the 1999 film "Grass," which explores the history of marijuana prohibition in the United States.
-
E.
Peggy Harper
Peggy Harper is best known as the former wife of American singer-songwriter Paul Simon.
- 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_69d6aa9687448190b28d353b1b6a610e |
completed | April 8, 2026, 7:20 p.m. |
| NER | Named-entity recognition | batch_69d797899a388190aa8fe813eac4dba7 |
completed | April 9, 2026, 12:11 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69e623e44c188190b5b83cf8f397554c |
completed | April 20, 2026, 1:02 p.m. |
| NEDg | Description generation | batch_69e62aee8fb88190b5973c61e692087f |
completed | April 20, 2026, 1:32 p.m. |
| NED2 | Entity disambiguation (via description) | batch_69e67394e7f081908fcc602c84eb4a65 |
completed | April 20, 2026, 6:42 p.m. |
Created at: April 8, 2026, 9:25 p.m.