Triple
T5140990
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Aunt Em |
E115950
|
entity |
| Predicate | name |
P16
|
FINISHED |
| Object |
Emily Gale
Emily Gale is the full name of Aunt Em, Dorothy's hardworking and caring aunt in L. Frank Baum's Oz series.
|
E526308
|
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: Emily Gale | Statement: [Aunt Em, name, Emily Gale]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Emily Gale Context triple: [Aunt Em, name, Emily Gale]
-
A.
Mary Wheeler
Mary Wheeler is a sibling of the renowned American theoretical physicist John Archibald Wheeler.
-
B.
Mary Hunt
Mary Hunt was a prominent American temperance reformer who led efforts to introduce and standardize anti-alcohol education in public schools during the late 19th and early 20th centuries.
-
C.
Alice Morgan
Alice Morgan is a brilliant but psychopathic scientist and Luther’s complex nemesis-ally in the British crime drama series "Luther."
-
D.
Betsy Blair
Betsy Blair was an American actress best known for her acclaimed, Oscar-nominated performance in the 1955 film "Marty" and for her work in both Hollywood and European cinema.
-
E.
Elizabeth Flanagan
Elizabeth Flanagan was the wife of C. Everett Koop, the prominent U.S. Surgeon General known for his influential public health advocacy.
- 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: Emily Gale Triple: [Aunt Em, name, Emily Gale]
Generated description
Emily Gale is the full name of Aunt Em, Dorothy's hardworking and caring aunt in L. Frank Baum's Oz series.
NED2
Entity disambiguation (via description)
gpt-5-mini-2025-08-07
Target entity: Emily Gale Target entity description: Emily Gale is the full name of Aunt Em, Dorothy's hardworking and caring aunt in L. Frank Baum's Oz series.
-
A.
Mary Wheeler
Mary Wheeler is a sibling of the renowned American theoretical physicist John Archibald Wheeler.
-
B.
Mary Hunt
Mary Hunt was a prominent American temperance reformer who led efforts to introduce and standardize anti-alcohol education in public schools during the late 19th and early 20th centuries.
-
C.
Alice Morgan
Alice Morgan is a brilliant but psychopathic scientist and Luther’s complex nemesis-ally in the British crime drama series "Luther."
-
D.
Betsy Blair
Betsy Blair was an American actress best known for her acclaimed, Oscar-nominated performance in the 1955 film "Marty" and for her work in both Hollywood and European cinema.
-
E.
Elizabeth Flanagan
Elizabeth Flanagan was the wife of C. Everett Koop, the prominent U.S. Surgeon General known for his influential public health advocacy.
- 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_69bd44459a988190a772a5c2ec6a1965 |
completed | March 20, 2026, 12:57 p.m. |
| NER | Named-entity recognition | batch_69bd787e5fe88190834042a73d4d9619 |
completed | March 20, 2026, 4:40 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69bfb70320ac819088ba3b1da868d9a4 |
completed | March 22, 2026, 9:31 a.m. |
| NEDg | Description generation | batch_69bfb783194081908002f857ff6f7ede |
completed | March 22, 2026, 9:33 a.m. |
| NED2 | Entity disambiguation (via description) | batch_69bfb7de05588190898383d8ac6ef494 |
completed | March 22, 2026, 9:35 a.m. |
Created at: March 20, 2026, 1:43 p.m.