Triple
T8395079
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Mordred |
E198032
|
entity |
| Predicate | siblingOf |
P363
|
FINISHED |
| Object | Gaheris |
E280797
|
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: Gaheris | Statement: [Mordred, siblingOf, Gaheris]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Gaheris Context triple: [Mordred, siblingOf, Gaheris]
-
A.
Gaheris
chosen
Gaheris is a knight of the Round Table in Arthurian legend, known as one of King Arthur’s nephews and a member of the Orkney clan.
-
B.
Baldwyn
Baldwyn is a masculine given name and surname of Old Germanic origin, historically associated with nobility and leadership.
-
C.
Gariadhar
Gariadhar is a town in the Bhavnagar district of Gujarat, India, known for its local markets and regional cultural significance.
-
D.
Lewelin
Lewelin is a variant spelling of the Welsh given name Llewelyn, historically borne by several medieval Welsh princes and nobles.
-
E.
Erigon
Erigon is a high-performance, modular Ethereum execution client focused on efficient resource usage and fast synchronization.
- 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_69ca82f816bc8190ab321c07d72208c1 |
completed | March 30, 2026, 2:04 p.m. |
| NER | Named-entity recognition | batch_69cb81874d6c8190bbc0ac832d8a339d |
completed | March 31, 2026, 8:10 a.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69ce02d5e0648190b33011c2ddca4ad3 |
completed | April 2, 2026, 5:47 a.m. |
Created at: March 30, 2026, 6:03 p.m.