Triple
T32476577
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Chinese space program |
E829990
|
entity |
| Predicate | firstLunarSampleReturn |
P107160
|
FINISHED |
| Object | Chang'e 5 |
E833345
|
NE 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: Chang'e 5 | Statement: [Chinese space program, firstLunarSampleReturn, Chang'e 5]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: firstLunarSampleReturn Context triple: [Chinese space program, firstLunarSampleReturn, Chang'e 5]
-
A.
firstLunarMissionReturnDate
Indicates the date on which the first lunar mission associated with an entity returned from the Moon.
-
B.
firstAsteroidWithSampleReturn
Indicates that the subject is the first asteroid from which a sample was successfully collected and returned to a receiving body (such as Earth).
-
C.
lunarMission
chosen
Indicates a mission or operation specifically directed toward exploring, studying, or traveling to the Moon.
-
D.
firstSuccessfulLander
Indicates that the subject entity is the earliest one to have successfully landed on the specified target or within the given context.
-
E.
firstMannedLunarOrbitMission
Indicates that the subject is the first mission in which humans successfully entered into orbit around the Moon.
- F. None of above.
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_69f3491ff3b48190b50a7fa00bb05b1f |
completed | April 30, 2026, 12:20 p.m. |
| NER | Named-entity recognition | batch_6a037c894b488190bcbec2eccaff4a01 |
completed | May 12, 2026, 7:16 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_6a34bcd49c3881909bb643aa1d000dbc |
completed | June 19, 2026, 3:51 a.m. |
| PD | Predicate disambiguation | batch_6a0379edf2d88190b492fca86ed23cac |
completed | May 12, 2026, 7:05 p.m. |
Created at: May 1, 2026, 12:58 a.m.