Triple
T32856351
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Banner in the Sky |
E840385
|
entity |
| Predicate | hasFictionalMountain |
P198554
|
FINISHED |
| Object | the Citadel |
—
|
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: the Citadel | Statement: [Banner in the Sky, hasFictionalMountain, the Citadel]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: hasFictionalMountain Context triple: [Banner in the Sky, hasFictionalMountain, the Citadel]
-
A.
hasMountain
Indicates that a location or region possesses or contains at least one mountain.
-
B.
homeMountainOf
Indicates that a particular mountain is the primary or native mountain associated with a given entity (such as a person, group, or organization).
-
C.
isMountOf
Indicates that one entity serves as the riding animal or mount for another entity.
-
D.
hasAncestralMountain
Indicates that an entity has a specific mountain recognized as its ancestral place of origin or heritage.
-
E.
hasMountainRange
Indicates that one entity possesses, contains, or is geographically associated with a specific mountain range.
- 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_69f349412c78819084459850e11d29f7 |
completed | April 30, 2026, 12:21 p.m. |
| NER | Named-entity recognition | batch_69fef2db323c8190821bda53f22a42be |
completed | May 9, 2026, 8:39 a.m. |
| PD | Predicate disambiguation | batch_69fef21d63c88190abf6a99b59b3c655 |
completed | May 9, 2026, 8:36 a.m. |
| PDg | Predicate description generation | batch_69fef2da7d388190a5712a5094741f18 |
completed | May 9, 2026, 8:39 a.m. |
Created at: May 1, 2026, 1:17 a.m.