Triple
T17765219
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | IR2 camera |
E443484
|
entity |
| Predicate | hostMissionName |
P92641
|
FINISHED |
| Object | PLANET-C |
—
|
NE NERFINISHED |
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: PLANET-C | Statement: [IR2 camera, hostMissionName, PLANET-C]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: PLANET-C Context triple: [IR2 camera, hostMissionName, PLANET-C]
-
A.
PLANET-C
chosen
PLANET-C, better known as Akatsuki, is a Japanese space probe designed to study the atmosphere and weather of Venus.
-
B.
PLANET-C spacecraft
PLANET-C, also known as Akatsuki, is a Japanese space probe developed by JAXA to study the atmosphere and climate of Venus from orbit.
-
C.
Terraplane
Terraplane was a British rock band from the 1980s best known as the precursor to the hard rock group Thunder.
-
D.
Species 8472
Species 8472 is a highly advanced, xenophobic, and nearly indestructible alien race from fluidic space in the Star Trek universe, known for their powerful biotechnology and resistance to assimilation.
-
E.
Calculon
Calculon is a melodramatic, egotistical robot soap-opera star from the animated television series Futurama.
- F. None of above.
- G. Unsure - the case is ambiguous/there is not enough information to decide.
Provenance (2 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_69d8b9edf16c8190a59ebd245d378f4f |
completed | April 10, 2026, 8:50 a.m. |
| NER | Named-entity recognition | batch_69e485fb2a3c81908887d1d36aee942d |
completed | April 19, 2026, 7:36 a.m. |
Created at: April 10, 2026, 10:11 a.m.