Triple
T11227490
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Emma C. Revell |
E265732
|
entity |
| Predicate | name |
P16
|
FINISHED |
| Object |
Emma C. Revell
Emma C. Revell is an individual whose specific public role or notability is not clearly identifiable from the given information.
|
E265732
|
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: Emma C. Revell | Statement: [Emma C. Revell, name, Emma C. Revell]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Emma C. Revell Context triple: [Emma C. Revell, name, Emma C. Revell]
-
A.
Emma C. Revell
Emma C. Revell was the wife of famed American evangelist Dwight L. Moody and a key supporter of his ministry and related religious work.
-
B.
Emma T. Townsend
Emma T. Townsend was the wife of prominent American steel industry magnate and U.S. Steel co-founder Elbert H. Gary.
-
C.
Emma E. Hickox
Emma E. Hickox is a British film editor known for her work on feature films such as "The Boat That Rocked."
-
D.
Elizabeth C. Ware
Elizabeth C. Ware was a benefactor whose financial support helped make possible the creation or acquisition of the renowned Blaschka Glass Models of Plants.
-
E.
Laura E. Richards
Laura E. Richards was an American author of children’s literature and biographies, known for works such as her Pulitzer Prize–winning biography of her mother, Julia Ward Howe.
- 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: Emma C. Revell Triple: [Emma C. Revell, name, Emma C. Revell]
Generated description
Emma C. Revell is an individual whose specific public role or notability is not clearly identifiable from the given information.
NED2
Entity disambiguation (via description)
gpt-5-mini-2025-08-07
Target entity: Emma C. Revell Target entity description: Emma C. Revell is an individual whose specific public role or notability is not clearly identifiable from the given information.
-
A.
Emma C. Revell
chosen
Emma C. Revell was the wife of famed American evangelist Dwight L. Moody and a key supporter of his ministry and related religious work.
-
B.
Emma T. Townsend
Emma T. Townsend was the wife of prominent American steel industry magnate and U.S. Steel co-founder Elbert H. Gary.
-
C.
Emma E. Hickox
Emma E. Hickox is a British film editor known for her work on feature films such as "The Boat That Rocked."
-
D.
Elizabeth C. Ware
Elizabeth C. Ware was a benefactor whose financial support helped make possible the creation or acquisition of the renowned Blaschka Glass Models of Plants.
-
E.
Laura E. Richards
Laura E. Richards was an American author of children’s literature and biographies, known for works such as her Pulitzer Prize–winning biography of her mother, Julia Ward Howe.
- F. None of above.
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_69d6aac656d48190b275efaa7d6074ee |
completed | April 8, 2026, 7:21 p.m. |
| NER | Named-entity recognition | batch_69d7e8ff7b40819089c835be710bc575 |
completed | April 9, 2026, 5:59 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69f60a4f804c81909abf5e9a88da1d91 |
completed | May 2, 2026, 2:29 p.m. |
| NEDg | Description generation | batch_69f61a13fd1481908a06ca65b276e0e1 |
completed | May 2, 2026, 3:36 p.m. |
| NED2 | Entity disambiguation (via description) | batch_69f61ad2bd0c8190ada37bc1f8ae160f |
completed | May 2, 2026, 3:40 p.m. |
Created at: April 8, 2026, 9:30 p.m.