Triple
T12716578
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Elizabeth Hadley Richardson |
E303856
|
entity |
| Predicate | dateOfDivorce (from Ernest Hemingway) |
P29197
|
FINISHED |
| Object | 1927 |
—
|
LITERAL 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: 1927 | Statement: [Elizabeth Hadley Richardson, dateOfDivorce (from Ernest Hemingway), 1927]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: dateOfDivorce (from Ernest Hemingway) Context triple: [Elizabeth Hadley Richardson, dateOfDivorce (from Ernest Hemingway), 1927]
-
A.
endTime (spouse: Ernest Hemingway)
Indicates the point in time at which the subject’s spousal relationship with Ernest Hemingway ended.
-
B.
end time of marriage with Humphrey Bogart
Indicates the date and time at which a person’s marriage to Humphrey Bogart ended.
-
C.
divorceDateWith
chosen
Indicates the date on which two entities legally ended their marriage to each other.
-
D.
marriageEndedBy
Indicates that a marriage relationship between two entities has been terminated due to the action or decision of a specified party or event.
-
E.
endTime (marriage to Joséphine)
Indicates the point in time at which the marriage to Joséphine legally or formally ended.
- F. None of above.
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_69d7bdf084148190ab9d513dc0735af4 |
completed | April 9, 2026, 2:55 p.m. |
| NER | Named-entity recognition | batch_69d9620bd6148190a2f50067a4c18c14 |
completed | April 10, 2026, 8:48 p.m. |
| PD | Predicate disambiguation | batch_69d960c088dc8190b0e63312c54e4c6c |
completed | April 10, 2026, 8:42 p.m. |
Created at: April 9, 2026, 5:23 p.m.