Triple
T7658236
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Epsilon Eridani b |
E173438
|
entity |
| Predicate | minimumMass_JupiterMass |
P69924
|
FINISHED |
| Object | about 0.8 |
—
|
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 0.8 | Statement: [Epsilon Eridani b, minimumMass_JupiterMass, about 0.8]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: minimumMass_JupiterMass Context triple: [Epsilon Eridani b, minimumMass_JupiterMass, about 0.8]
-
A.
massRelativeToJupiter
Indicates the mass of an entity expressed as a ratio or multiple of Jupiter’s mass.
-
B.
massInJupiterOrbit
Indicates the mass an object has while it is located in orbit around Jupiter.
-
C.
planetMinimumMass
chosen
Indicates the minimum mass threshold that a planet must have, typically expressed relative to a reference unit (e.g., Earth or Jupiter masses).
-
D.
radiusRelativeToJupiter
Indicates that the radius of one object is expressed as a value relative to the radius of Jupiter.
-
E.
brightnessComparedToJupiter
Indicates how the brightness of one object compares to that of Jupiter.
- 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_69c69955517c819085bc715b96d304d2 |
completed | March 27, 2026, 2:51 p.m. |
| NER | Named-entity recognition | batch_69c7061cbc3c8190a917dd7e71214182 |
completed | March 27, 2026, 10:35 p.m. |
| PD | Predicate disambiguation | batch_69c7015dd8fc8190bc5f52a12bd46209 |
completed | March 27, 2026, 10:14 p.m. |
Created at: March 27, 2026, 3:59 p.m.