Triple
T5969814
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Rigel |
E132843
|
entity |
| Predicate | positionInOrion |
P66368
|
FINISHED |
| Object | marks Orion’s left foot as seen from Earth |
—
|
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: marks Orion’s left foot as seen from Earth | Statement: [Rigel, positionInOrion, marks Orion’s left foot as seen from Earth]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: positionInOrion Context triple: [Rigel, positionInOrion, marks Orion’s left foot as seen from Earth]
-
A.
positionInAsterism
chosen
Indicates the specific location or role that an object occupies within a defined asterism pattern.
-
B.
brightnessRankInOrion
Indicates the relative ordering of a celestial object's brightness specifically among objects located in the Orion constellation.
-
C.
positionInRingSystem
Indicates the specific location or ordering of an object within a ring system relative to the system’s central body and/or other ring components.
-
D.
rankByBrightnessInOrion
Indicates the ordering of entities based on their relative brightness within the Orion region.
-
E.
positionInCosmos
Indicates the spatial or hierarchical location of an entity within the broader structure of the cosmos or universe.
- 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_69c0086deab081908550159ca23eec9b |
completed | March 22, 2026, 3:19 p.m. |
| NER | Named-entity recognition | batch_69c03e174c7c8190b04113f6529f5f0e |
completed | March 22, 2026, 7:08 p.m. |
| PD | Predicate disambiguation | batch_69c0335b55a48190927a5b1529edb542 |
completed | March 22, 2026, 6:22 p.m. |
Created at: March 22, 2026, 4:03 p.m.