Triple
T18170791
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Anubis chapel |
E435018
|
entity |
| Predicate | dedicatedTo |
P500
|
FINISHED |
| Object | Anubis |
—
|
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: Anubis | Statement: [Anubis chapel, dedicatedTo, Anubis]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Anubis Context triple: [Anubis chapel, dedicatedTo, Anubis]
-
A.
Anubis
chosen
Anubis is the ancient Egyptian god of mummification and the afterlife, typically depicted as a jackal-headed figure who guides and protects souls of the dead.
-
B.
Nephthys
Nephthys is an ancient Egyptian goddess associated with mourning, protection, and the night, often depicted as the sister of Isis and Osiris and the wife of Set.
-
C.
Osiris
Osiris is the ancient Egyptian god of the afterlife, resurrection, and fertility, often depicted as a mummified king and central to Egyptian funerary religion.
-
D.
Khonsu
Khonsu is an ancient Egyptian lunar god associated with time, healing, and protection, often worshipped as the son of Amun and Mut.
-
E.
Hath-Set
Hath-Set is a recurring DC Comics supervillain and ancient Egyptian priest cursed to eternally oppose Hawkman and Hawkgirl across their many reincarnated lives.
- 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_69d8b90b7a188190b3fc7b8d4a6cd20a |
completed | April 10, 2026, 8:47 a.m. |
| NER | Named-entity recognition | batch_69e4df56190c8190a3644333f9050a10 |
completed | April 19, 2026, 1:57 p.m. |
Created at: April 10, 2026, 10:30 a.m.