Triple
T18770922
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Orion |
E459014
|
entity |
| Predicate | containsBrightStar |
P23774
|
FINISHED |
| Object | Rigel |
—
|
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: Rigel | Statement: [Orion, containsBrightStar, Rigel]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Rigel Context triple: [Orion, containsBrightStar, Rigel]
-
A.
Rigel
chosen
Rigel is a luminous blue supergiant star and one of the brightest stars in the night sky, prominently marking the foot of the constellation Orion.
-
B.
Betelgeuse
Betelgeuse is a massive red supergiant star in the constellation Orion, notable for its brightness and status as a likely future supernova.
-
C.
Aldebaran
Aldebaran is a bright orange giant star in the constellation Taurus, known as one of the most prominent stars in the night sky.
-
D.
Aldebaran
Aldebaran is the internal codename for AMD’s high-performance Instinct MI250X data center GPU architecture designed for accelerated computing and HPC workloads.
-
E.
Zeta Orionis
Zeta Orionis, traditionally known as Alnitak, is a massive, hot blue multiple star system forming the easternmost star of Orion’s Belt.
- 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_69d8d395dba0819087568404508590cb |
completed | April 10, 2026, 10:40 a.m. |
| NER | Named-entity recognition | batch_69e59335a01881908731371be1e27a6b |
completed | April 20, 2026, 2:45 a.m. |
Created at: April 10, 2026, 11:52 a.m.