Triple
T16321692
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Fanny Hayes |
E396307
|
entity |
| Predicate | name |
P16
|
FINISHED |
| Object | Fanny Hayes |
E396307
|
NE FINISHED |
How this triple was built (2 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: Fanny Hayes | Statement: [Fanny Hayes, name, Fanny Hayes]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Fanny Hayes Context triple: [Fanny Hayes, name, Fanny Hayes]
-
A.
Fanny Hayes
chosen
Fanny Hayes was the daughter of U.S. President Rutherford B. Hayes and First Lady Lucy Webb Hayes, who grew up in the White House during her father's administration.
-
B.
Fanny Hayes
Fanny Hayes was the mother of pioneering African American lyric tenor and composer Roland Hayes, who became one of the first internationally acclaimed Black concert artists.
-
C.
Faye Medwick
Faye Medwick is a fictional character appearing in the work titled "Chapter Two."
-
D.
Faye Miller
Faye Miller is a market research psychologist who becomes one of Don Draper’s significant romantic partners in the television series "Mad Men."
-
E.
Faye Ward
Faye Ward is a British film and television producer known for her work on acclaimed projects such as the historical drama "Suffragette."
- F. None of above.
- G. Unsure - the case is ambiguous/there is not enough information to decide.
Provenance (3 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_69d87f255b788190a400eba031dd85d8 |
completed | April 10, 2026, 4:40 a.m. |
| NER | Named-entity recognition | batch_69e296b706108190b43a05b784633050 |
completed | April 17, 2026, 8:23 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_6a0035537d188190a88753d58939faf4 |
completed | May 10, 2026, 7:35 a.m. |
Created at: April 10, 2026, 5:06 a.m.