Triple
T12827841
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Lord of the Earth |
E306702
|
entity |
| Predicate | refersTo |
P37
|
FINISHED |
| Object | Geb |
E59547
|
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: Geb | Statement: [Lord of the Earth, refersTo, Geb]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Geb Context triple: [Lord of the Earth, refersTo, Geb]
-
A.
Geb
chosen
Geb is the ancient Egyptian god of the earth, often depicted as a reclining man beneath the sky goddess Nut and associated with fertility, vegetation, and the underworld.
-
B.
Shapash
Shapash is the Phoenician sun goddess, often depicted as a powerful celestial deity associated with light, justice, and guidance among the gods and humans.
-
C.
Nebmaatre
Nebmaatre was the throne name of the ancient Egyptian pharaoh Amenhotep III, a powerful ruler of the 18th Dynasty known for his prosperous and artistically rich reign.
-
D.
El-Zabu
El-Zabu is a small settlement located within Egypt’s Bahariya Oasis in the Western Desert.
-
E.
Wepwawet
Wepwawet is an ancient Egyptian jackal-headed war and funerary god, often depicted as a path-opener who guided kings and the dead.
- 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_69d7bdf52b94819096d6f0ba4ab50a98 |
completed | April 9, 2026, 2:55 p.m. |
| NER | Named-entity recognition | batch_69d96fae51608190a50970bd038359a5 |
completed | April 10, 2026, 9:46 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69f68ed4f7388190ba989b8a79bd7c6d |
completed | May 2, 2026, 11:55 p.m. |
Created at: April 9, 2026, 5:33 p.m.