Triple
T17775300
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Hulishan Fortress |
E443751
|
entity |
| Predicate | artilleryWeight |
P128888
|
FINISHED |
| Object | approximately 60 tons |
—
|
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: approximately 60 tons | Statement: [Hulishan Fortress, artilleryWeight, approximately 60 tons]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: artilleryWeight Context triple: [Hulishan Fortress, artilleryWeight, approximately 60 tons]
-
A.
artilleryType
Indicates the specific category or kind of artillery associated with an entity or event.
-
B.
artilleryUsedBy
Indicates that a particular artillery asset is operated or employed by a specified user, such as a military unit, organization, or country.
-
C.
hasArtilleryCaliber
Indicates that an artillery piece is characterized by or equipped with a specific caliber (diameter) of its gun barrel or ammunition.
-
D.
artilleryPiecesUsed
Indicates that certain artillery pieces were employed or deployed in a particular action, event, or context.
-
E.
artilleryUsedIn
Indicates that a particular piece or type of artillery is employed or deployed in a specific event, operation, or context.
- 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_69d8b9ef17708190bdf7e2adbf14ddc2 |
completed | April 10, 2026, 8:50 a.m. |
| NER | Named-entity recognition | batch_69e4871c23408190aae7f1a2c77a10cb |
completed | April 19, 2026, 7:41 a.m. |
| PD | Predicate disambiguation | batch_69e3d8d8e538819084f1584426b41d5e |
completed | April 18, 2026, 7:17 p.m. |
| PDg | Predicate description generation | batch_69e3db7704588190a34a422421152173 |
completed | April 18, 2026, 7:28 p.m. |
Created at: April 10, 2026, 10:12 a.m.