Triple
T5373622
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Tar Heels |
E108907
|
entity |
| Predicate | mascot |
P52
|
FINISHED |
| Object | Rameses |
E112593
|
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: Rameses | Statement: [Tar Heels, mascot, Rameses]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Rameses Context triple: [Tar Heels, mascot, Rameses]
-
A.
Rameses
chosen
Rameses is the ram mascot of the University of North Carolina at Chapel Hill, symbolizing the school's athletic teams and spirit.
-
B.
Pi-Ramesses
Pi-Ramesses was a major royal city in the Nile Delta that served as the principal residence and power center of Ramesses II during Egypt’s New Kingdom.
-
C.
Ramesses II
Ramesses II was a powerful 19th Dynasty pharaoh of ancient Egypt, renowned for his extensive building projects, military campaigns, and exceptionally long reign.
-
D.
Kahmunrah
Kahmunrah is the power-hungry ancient Egyptian pharaoh and main antagonist in the film "Night at the Museum: Battle of the Smithsonian."
-
E.
Pharaoh
Pharaoh is the title used for the ancient kings of Egypt, who ruled as powerful monarchs and were often regarded as divine or semi-divine figures.
- 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_69bd440c77948190aad2a5f39b7b80f5 |
completed | March 20, 2026, 12:56 p.m. |
| NER | Named-entity recognition | batch_69bd86abc1e88190ad08279c3bf238e5 |
completed | March 20, 2026, 5:40 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69bf6c4cdec48190908b52a37b82c2d1 |
completed | March 22, 2026, 4:13 a.m. |
Created at: March 20, 2026, 2:03 p.m.