Triple
T35119245
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | the Iron Throne |
E1014121
|
entity |
| Predicate | notableRulerToSit |
P60298
|
FINISHED |
| Object | Robert Baratheon |
E317751
|
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: Robert Baratheon | Statement: [the Iron Throne, notableRulerToSit, Robert Baratheon]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: notableRulerToSit Context triple: [the Iron Throne, notableRulerToSit, Robert Baratheon]
-
A.
recognizedAsRulersBy
Indicates that certain entities are acknowledged or accepted by others as their legitimate rulers or authorities.
-
B.
notableMonarch
Indicates that the subject is a monarch who is distinguished or historically significant in some notable way.
-
C.
coRulership
Indicates a relationship in which two or more entities share authority or power to rule jointly over the same domain or group.
-
D.
rulerOf
chosen
Indicates that one entity holds governing authority or sovereignty over another entity, such as a person ruling a country or territory.
-
E.
associatedDynastyRuler
Indicates a relationship where a dynasty is linked to the ruler who governed or is historically connected with it.
- F. None of above.
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_69f76dd8b6948190aaa32b081816bd94 |
completed | May 3, 2026, 3:46 p.m. |
| NER | Named-entity recognition | batch_6a037c8c34f88190ace26f555827f23e |
completed | May 12, 2026, 7:16 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_6a3823ae4e54819083152f8611939e80 |
completed | June 21, 2026, 5:47 p.m. |
| PD | Predicate disambiguation | batch_6a037a016960819093ed4990fb4d9d36 |
completed | May 12, 2026, 7:05 p.m. |
Created at: May 3, 2026, 4:01 p.m.