Triple
T1981599
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Second voyage of James Cook |
E43037
|
entity |
| Predicate | firstAntarcticCircleCrossingDate |
P35756
|
FINISHED |
| Object | 1773-01-17 |
—
|
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: 1773-01-17 | Statement: [Second voyage of James Cook, firstAntarcticCircleCrossingDate, 1773-01-17]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: firstAntarcticCircleCrossingDate Context triple: [Second voyage of James Cook, firstAntarcticCircleCrossingDate, 1773-01-17]
-
A.
hasTropicOfCapricornCrossing
Indicates that the referenced geographic entity is intersected or crossed by the Tropic of Capricorn.
-
B.
firstWinterAscentDate
Indicates the calendar date on which the first successful winter ascent of something (typically a route, peak, or climb) was completed.
-
C.
startTimeOfCircumnavigation
Indicates the specific time at which a circumnavigation event begins.
-
D.
firstChineseAntarcticStation
Indicates that the subject is the first Antarctic research station established by China.
-
E.
firstWinterAscentYear
Indicates the year in which the first successful winter ascent of something (such as a mountain or route) was completed.
- F. None of above. chosen
Provenance (4 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_69a88713ddc88190a969715658ebe7a8 |
completed | March 4, 2026, 7:25 p.m. |
| NER | Named-entity recognition | batch_69abb96f932881908bebfc4176fda7c0 |
completed | March 7, 2026, 5:36 a.m. |
| PD | Predicate disambiguation | batch_69abb798d288819083132cf14605bd02 |
completed | March 7, 2026, 5:28 a.m. |
| PDg | Predicate description generation | batch_69abb96e07c08190beed60096e9d71b4 |
completed | March 7, 2026, 5:36 a.m. |
Created at: March 4, 2026, 7:37 p.m.