Triple
T28599834
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Tiangong-2 |
E723877
|
entity |
| Predicate | longestCrewedStayDuration |
P40964
|
FINISHED |
| Object | about 30 days |
—
|
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: about 30 days | Statement: [Tiangong-2, longestCrewedStayDuration, about 30 days]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: longestCrewedStayDuration Context triple: [Tiangong-2, longestCrewedStayDuration, about 30 days]
-
A.
wasLongestShuttleMissionAtTheTime
Indicates that a particular shuttle mission held the record for being the longest in duration at the time it occurred.
-
B.
longestDurationAt
chosen
Indicates that one entity has the greatest length of time associated with a particular state, event, or activity compared to other relevant entities.
-
C.
lastCrewReturnDate
Indicates the date on which the most recent crew associated with the entity returned.
-
D.
firstISSLongDurationMissionEnd
Indicates the date or event marking the conclusion of the first long-duration mission aboard the International Space Station.
-
E.
timeInSpace
Indicates the amount of time an entity has spent in outer space.
- 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_69f01d80b1908190980594837604b8c7 |
completed | April 28, 2026, 2:37 a.m. |
| NER | Named-entity recognition | batch_69f652a492108190b885b955ce147d3c |
completed | May 2, 2026, 7:38 p.m. |
| PD | Predicate disambiguation | batch_69f651aad92c8190b874b3b5f9f64434 |
completed | May 2, 2026, 7:34 p.m. |
Created at: April 28, 2026, 4:23 a.m.