Triple
T28889736
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Stewards of Gondor |
E732663
|
entity |
| Predicate | thronePolicy |
P165490
|
FINISHED |
| Object | left the throne of Gondor empty |
—
|
LITERAL 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: left the throne of Gondor empty | Statement: [Stewards of Gondor, thronePolicy, left the throne of Gondor empty]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: thronePolicy Context triple: [Stewards of Gondor, thronePolicy, left the throne of Gondor empty]
-
A.
throne
Indicates that an entity holds or occupies a position of sovereign authority or rulership, typically as a monarch.
-
B.
throneName
Indicates the official royal or regnal name adopted by a ruler when they ascend to the throne.
-
C.
securedThroneBy
Indicates that one entity obtained or maintained a throne or rulership position through the actions, support, or intervention of another entity.
-
D.
acceptedThrone
Indicates that an entity has agreed to assume and take on the role and authority associated with a throne or rulership.
-
E.
throneCity
Indicates the city where a ruler’s throne or primary seat of authority is located.
- 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_69f05b07bdec819080cadfe147aa1f25 |
completed | April 28, 2026, 7 a.m. |
| NER | Named-entity recognition | batch_69f65a744e1c8190bff56db4cb0b68df |
completed | May 2, 2026, 8:11 p.m. |
| PD | Predicate disambiguation | batch_69f6576487e081908d802f1caf59c423 |
completed | May 2, 2026, 7:58 p.m. |
| PDg | Predicate description generation | batch_69f65875030881909007c502b7dcc998 |
completed | May 2, 2026, 8:03 p.m. |
Created at: April 28, 2026, 7:54 a.m.