Triple
T36289393
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Rickard Stark |
E893180
|
entity |
| Predicate | predecessorAsLordOfWinterfell |
P195985
|
FINISHED |
| Object | Edwyle Stark |
—
|
NE NERFINISHED |
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: Edwyle Stark | Statement: [Rickard Stark, predecessorAsLordOfWinterfell, Edwyle Stark]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: predecessorAsLordOfWinterfell Context triple: [Rickard Stark, predecessorAsLordOfWinterfell, Edwyle Stark]
-
A.
predecessorOnDragonstone
Indicates that one entity previously held a position, role, or status on Dragonstone before another entity.
-
B.
firstBaratheonKing
Indicates that the subject is the first member of House Baratheon to hold the title of king.
-
C.
predecessorAsHeir
Indicates that one entity previously held the status of heir before being succeeded by another in that role.
-
D.
predecessorAsDukeOfBrittany
Indicates that one entity previously held the title of Duke of Brittany immediately before another entity.
-
E.
predecessorAsDauphin
Indicates that one entity previously held the title or role of Dauphin immediately before another entity.
- F. None of above. chosen
Provenance (4 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_69f76e4955c08190b8cfddca34fc0242 |
completed | May 3, 2026, 3:48 p.m. |
| NER | Named-entity recognition | batch_69fdfbafe32081909c62653ff4fc155c |
completed | May 8, 2026, 3:05 p.m. |
| PD | Predicate disambiguation | batch_69fdf64db4a881908f8250e24ae3cefb |
completed | May 8, 2026, 2:42 p.m. |
| PDg | Predicate description generation | batch_69fdfbae00e481908a2e4558b9dee07e |
completed | May 8, 2026, 3:05 p.m. |
Created at: May 3, 2026, 4:09 p.m.