Triple
T7762006
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Luna |
E176043
|
entity |
| Predicate | hadTempleDedicatedTo |
P28305
|
FINISHED |
| Object | Luna (Roman moon goddess) |
E111954
|
NE 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: Luna (Roman moon goddess) | Statement: [Luna, hadTempleDedicatedTo, Luna (Roman moon goddess)]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Luna (Roman moon goddess) Context triple: [Luna, hadTempleDedicatedTo, Luna (Roman moon goddess)]
-
A.
Selene
Selene is the tourist lunar excursion vehicle featured in Arthur C. Clarke’s science fiction novel "A Fall of Moondust."
-
B.
Selene
chosen
Selene is the Greek goddess and personification of the Moon, often depicted driving a silver chariot across the night sky.
-
C.
Luna
Luna is a Spanish surname most prominently associated with Mexican actor and filmmaker Diego Luna.
-
D.
Luna
Luna is the natural satellite of Earth, renowned for its phases, influence on tides, and prominence in human culture and mythology.
-
E.
Luna
Luna was an ancient Roman town in northern Italy that served as a key urban and commercial center for the Ligurian region.
- F. None of above.
- G. Unsure - the case is ambiguous/there is not enough information to decide.
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_69c69962923c8190ac74d28b4f9fe0a0 |
completed | March 27, 2026, 2:51 p.m. |
| NER | Named-entity recognition | batch_69c70404c2108190ad2b900ac9bf582b |
completed | March 27, 2026, 10:26 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69c8c7d658888190af97b83127086a2b |
completed | March 29, 2026, 6:33 a.m. |
Created at: March 27, 2026, 4:09 p.m.