Triple
T22215958
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Elisabeth–Descartes correspondence |
E549073
|
entity |
| Predicate | latestLettersDate |
P21092
|
FINISHED |
| Object | 1649 |
—
|
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: 1649 | Statement: [Elisabeth–Descartes correspondence, latestLettersDate, 1649]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: latestLettersDate Context triple: [Elisabeth–Descartes correspondence, latestLettersDate, 1649]
-
A.
latestPossibleDate
Indicates the most recent date on which a given event, condition, or state can validly or feasibly occur.
-
B.
lastEntryDate
chosen
Indicates the date on which the most recent entry, record, or update associated with the subject occurred.
-
C.
latestReleaseDate
Indicates the date on which the most recent version or release of an entity became available.
-
D.
latestEntriesDateFrom
Indicates the starting date from which the most recent entries in a set or system are considered or retrieved.
-
E.
latestTime
Indicates the most recent point in time at which the related event, state, or condition occurs or is valid among a set of possible times.
- 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_69e11e3f7e04819089806d81d5ac431e |
completed | April 16, 2026, 5:37 p.m. |
| NER | Named-entity recognition | batch_69f12b8bdfbc8190832809edbe8b7c27 |
completed | April 28, 2026, 9:50 p.m. |
| PD | Predicate disambiguation | batch_69e71b4dcc408190a30429fb08fcf39e |
completed | April 21, 2026, 6:38 a.m. |
Created at: April 16, 2026, 8:37 p.m.