Triple
T868987
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Mercury |
E18768
|
entity |
| Predicate | solarDayLength |
P2027
|
FINISHED |
| Object | about 176 Earth 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 176 Earth days | Statement: [Mercury, solarDayLength, about 176 Earth days]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: solarDayLength Context triple: [Mercury, solarDayLength, about 176 Earth days]
-
A.
hasSolarDayLength
chosen
Indicates that an entity is associated with a specific duration for one complete solar day (the time between successive noons).
-
B.
dayLengthCharacteristic
Indicates a relationship where an entity is characterized or defined by the length or duration of its day.
-
C.
solarPosition
Indicates the spatial orientation or location of an entity relative to the Sun at a given time.
-
D.
solarDeclinationAtOverheadSun
Indicates the angular position of the sun north or south of the celestial equator at the location where it is directly overhead.
-
E.
forSunApprox
Indicates that something is approximately intended or suitable for use with, by, or in relation to the Sun, rather than being an exact or strictly defined solar relation.
- 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_69a4938ce8688190a24bdfef82ba7d21 |
completed | March 1, 2026, 7:29 p.m. |
| NER | Named-entity recognition | batch_69a4ac7f98908190883f71049092c7c8 |
completed | March 1, 2026, 9:15 p.m. |
| PD | Predicate disambiguation | batch_69a4aa87504481909618a6815948da6f |
completed | March 1, 2026, 9:07 p.m. |
Created at: March 1, 2026, 7:39 p.m.