Triple
T16621753
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Laena Velaryon |
E403848
|
entity |
| Predicate | dragon |
P52720
|
FINISHED |
| Object | Vhagar |
E1085746
|
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: Vhagar | Statement: [Laena Velaryon, dragon, Vhagar]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Vhagar Context triple: [Laena Velaryon, dragon, Vhagar]
-
A.
Vhagar
chosen
Vhagar is one of the most powerful and ancient dragons in Westerosi history, famed for her pivotal role in the Targaryen civil war known as the Dance of the Dragons.
-
B.
Gwaihir
Gwaihir is a mighty Great Eagle from J.R.R. Tolkien’s Middle-earth legendarium, best known for aiding Gandalf and participating in key rescues during The Lord of the Rings.
-
C.
Holdsclaw
Holdsclaw is the surname of Chamique Holdsclaw, a prominent former American professional basketball player and Women’s Basketball Hall of Famer.
-
D.
Wyvern
Wyvern is a minor crew member of the cursed ghost ship Flying Dutchman in the Pirates of the Caribbean film series.
-
E.
Cauldron Snout
Cauldron Snout is a long, rocky cascade on the River Tees in northern England, known for its dramatic scenery along the Pennine Way.
- 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_69d883897eb481909eaaa088ba9918d9 |
completed | April 10, 2026, 4:58 a.m. |
| NER | Named-entity recognition | batch_69e3754e80ec8190b3c66b33dbc7463c |
completed | April 18, 2026, 12:13 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_6a007db27f788190a3c57b7ea8a8a9c6 |
completed | May 10, 2026, 12:44 p.m. |
Created at: April 10, 2026, 5:17 a.m.