Triple
T32185090
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Narrative of the Captivity and Restoration of Mrs. Mary Rowlandson |
E822085
|
entity |
| Predicate | yearOfEventsDepicted |
P54917
|
FINISHED |
| Object | 1675 |
—
|
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: 1675 | Statement: [Narrative of the Captivity and Restoration of Mrs. Mary Rowlandson, yearOfEventsDepicted, 1675]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: yearOfEventsDepicted Context triple: [Narrative of the Captivity and Restoration of Mrs. Mary Rowlandson, yearOfEventsDepicted, 1675]
-
A.
yearDepicted
chosen
Indicates the specific year in which the subject is portrayed, represented, or set.
-
B.
yearOfEventSupport
Indicates the specific year in which support for a particular event occurred or was provided.
-
C.
hasHistoricEventYear
Indicates the specific year in which a referenced historic event took place.
-
D.
yearObserved
Indicates the specific calendar year during which the referenced event, condition, or measurement was observed or recorded.
-
E.
yearOfPassage
Indicates the specific calendar year in which a law, bill, or formal measure was officially passed or enacted.
- 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_69f3490755288190aee11740a34862f9 |
completed | April 30, 2026, 12:20 p.m. |
| NER | Named-entity recognition | batch_69fd37b695c88190855801626f91c4cd |
completed | May 8, 2026, 1:09 a.m. |
| PD | Predicate disambiguation | batch_69fd374cccf08190a230e87164af5938 |
completed | May 8, 2026, 1:07 a.m. |
Created at: May 1, 2026, 12:35 a.m.