Triple
T33111675
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | High Kingship of the Dúnedain |
E847347
|
entity |
| Predicate | capitalInitiallyAt |
P30016
|
FINISHED |
| Object | Arnor |
—
|
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: Arnor | Statement: [High Kingship of the Dúnedain, capitalInitiallyAt, Arnor]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: capitalInitiallyAt Context triple: [High Kingship of the Dúnedain, capitalInitiallyAt, Arnor]
-
A.
capitalAtBeginning
Indicates that a string or word has a capital (uppercase) letter as its first character.
-
B.
capitalSince
chosen
Indicates that an entity has served as the capital of another entity starting from a specified point in time.
-
C.
capital
Indicates that one place serves as the official seat of government or primary administrative center for another political entity.
-
D.
capitalPreviouslyAt
Indicates that an entity once served as the capital of another entity in the past, but no longer holds that status.
-
E.
capitalRenamedFrom
Indicates that a capital city previously had a different name, specifying the former name from which it was renamed.
- 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_69f3495751a081909850af5843da40dc |
completed | April 30, 2026, 12:21 p.m. |
| NER | Named-entity recognition | batch_69fd4d1854988190be093b103a681798 |
completed | May 8, 2026, 2:40 a.m. |
| PD | Predicate disambiguation | batch_69fd4c8d1a188190897c24527337814a |
completed | May 8, 2026, 2:38 a.m. |
Created at: May 1, 2026, 1:27 a.m.