Triple
T8395080
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Mordred |
E198032
|
entity |
| Predicate | siblingOf |
P363
|
FINISHED |
| Object | Agravain |
E278677
|
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: Agravain | Statement: [Mordred, siblingOf, Agravain]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Agravain Context triple: [Mordred, siblingOf, Agravain]
-
A.
Agravain
chosen
Agravain is a knight of the Round Table in Arthurian legend, known as one of Gawain’s brothers and often portrayed as treacherous or antagonistic.
-
B.
Lancelot Heath
Lancelot Heath is an individual notable enough to be recognized as a prominent bearer of the surname Heath.
-
C.
Æschere
Æschere is a trusted advisor and close companion of King Hrothgar in the Old English epic Beowulf, whose death at the hands of Grendel’s mother spurs Beowulf’s vengeful pursuit.
-
D.
Knight of the Bath
The Knight of the Bath is a rank of knighthood within the British Order of the Bath, historically bestowed as a high honor for distinguished military or civil service.
-
E.
Sir Bedivere
Sir Bedivere is a knight of Arthurian legend best known for returning King Arthur’s sword Excalibur to the Lady of the Lake after the Battle of Camlann.
- 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_69cde85ee7b08190bfbcbed0edb142dd |
completed | April 2, 2026, 3:54 a.m. |
Created at: March 30, 2026, 6:03 p.m.