Triple
T7105388
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Memnon |
E165567
|
entity |
| Predicate | hasVariant |
P455
|
FINISHED |
| Object | Aethiopian Memnon |
E644196
|
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: Aethiopian Memnon | Statement: [Memnon, hasVariant, Aethiopian Memnon]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Aethiopian Memnon Context triple: [Memnon, hasVariant, Aethiopian Memnon]
-
A.
Memnon of Aethiopia
chosen
Memnon of Aethiopia is a legendary Ethiopian king and warrior in Greek mythology who fought on the side of Troy during the Trojan War and was slain by Achilles.
-
B.
Mastallone
Mastallone is a mountain stream in northern Italy that flows through the Piedmont region before joining the Sesia River.
-
C.
Rekhetre
Rekhetre was an ancient Egyptian queen of the 4th Dynasty, known primarily as one of the wives of Pharaoh Menkaure.
-
D.
Sawiris
Sawiris is a prominent Egyptian business family best known for its influential role in construction, telecommunications, and investment through the Orascom group of companies.
-
E.
Khnum
Khnum is an ancient Egyptian ram-headed god associated with the Nile’s inundation, creation, and the molding of human beings on a potter’s wheel.
- 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_69c6887fcddc8190a5d58908f6dee590 |
completed | March 27, 2026, 1:39 p.m. |
| NER | Named-entity recognition | batch_69c6e5b892008190827fa1e5eab2e558 |
completed | March 27, 2026, 8:16 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69c7ad83aa288190b06262ac9898f5c1 |
completed | March 28, 2026, 10:29 a.m. |
Created at: March 27, 2026, 2:42 p.m.