Triple
T10457805
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Daenerys Targaryen |
E246590
|
entity |
| Predicate | spouse |
P13
|
FINISHED |
| Object | Khal Drogo |
E832062
|
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: Khal Drogo | Statement: [Daenerys Targaryen, spouse, Khal Drogo]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Khal Drogo Context triple: [Daenerys Targaryen, spouse, Khal Drogo]
-
A.
Khal Drogo
chosen
Khal Drogo is a fearsome Dothraki warlord from the series "Game of Thrones," known for his unmatched prowess in battle and his marriage to Daenerys Targaryen.
-
B.
Drogo
Drogo was an 11th-century Norman nobleman and military leader from the Hauteville family who became Count of Apulia in southern Italy.
-
C.
Mance Rayder
Mance Rayder is a prominent character in the "Game of Thrones" series, known as the charismatic and unifying leader of the Free Folk beyond the Wall.
-
D.
Daario Naharis
Daario Naharis is a flamboyant and ruthless Tyroshi sellsword captain who becomes a close ally and lover of Daenerys Targaryen in the A Song of Ice and Fire series.
-
E.
Kylos
Kylos is the destroyed home planet of Drax the Destroyer in the Marvel universe.
- 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_69d381c04fe08190957c26c526a3b05a |
completed | April 6, 2026, 9:49 a.m. |
| NER | Named-entity recognition | batch_69d4fe4a56e08190ab56d762d6a91b01 |
completed | April 7, 2026, 12:53 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69d87f182cb481909f838d6d1dfa7e79 |
completed | April 10, 2026, 4:39 a.m. |
Created at: April 6, 2026, 12:18 p.m.