Triple
T36611744
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Stewards of Gondor |
E903481
|
entity |
| Predicate | relationshipToThrone |
P99936
|
FINISHED |
| Object | guardians of the throne |
—
|
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: guardians of the throne | Statement: [Stewards of Gondor, relationshipToThrone, guardians of the throne]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: relationshipToThrone Context triple: [Stewards of Gondor, relationshipToThrone, guardians of the throne]
-
A.
relatedThrone
chosen
Indicates a relationship in which an entity is connected or associated with a throne, typically through possession, claim, succession, or authority over it.
-
B.
relationshipToPrincess
Indicates the specific familial, social, or romantic connection that one entity has to a princess.
-
C.
rankWithinImperialFamily
Indicates the hierarchical position an individual holds within an imperial family relative to other family members.
-
D.
childOfMonarch
Indicates that one entity is the offspring (biological or legally recognized) of another entity who holds or held the status of monarch.
-
E.
siblingOfMonarch
Indicates that one person is a sibling (brother or sister) of a reigning or former monarch.
- F. None of above.
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_69f76e6960e4819092047756ceb9a17e |
completed | May 3, 2026, 3:48 p.m. |
| NER | Named-entity recognition | batch_6a037c8e2c648190a65fc9c7872861af |
completed | May 12, 2026, 7:16 p.m. |
| PD | Predicate disambiguation | batch_6a037a0bf4b88190bdcfae9a14b51f0a |
completed | May 12, 2026, 7:05 p.m. |
Created at: May 3, 2026, 4:11 p.m.