Triple
T33980976
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | HMS Duncan |
E871280
|
entity |
| Predicate | navalGun |
P88584
|
FINISHED |
| Object | 4.5 inch Mark 8 naval gun |
—
|
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: 4.5 inch Mark 8 naval gun | Statement: [HMS Duncan, navalGun, 4.5 inch Mark 8 naval gun]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: navalGun Context triple: [HMS Duncan, navalGun, 4.5 inch Mark 8 naval gun]
-
A.
gunDeckArmament
Indicates the type or configuration of weapons mounted on a ship’s gun deck.
-
B.
numberOfMainBatteryGuns
Indicates the quantity of primary (main) battery guns that an entity, typically a warship or similar platform, is equipped with.
-
C.
primaryArmament
Indicates the main weapon or principal offensive system that an entity (such as a vehicle, vessel, or platform) is equipped with or uses.
-
D.
lightArmament
Indicates that an entity is equipped with or characterized by relatively minimal or lightweight weaponry compared to standard or heavy armament.
-
E.
mainGunModel
chosen
Indicates the specific model or type designation of the primary gun or main weapon system used by an entity.
- 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_69f3499da0188190ab1a4ff06fb06a2a |
completed | April 30, 2026, 12:22 p.m. |
| NER | Named-entity recognition | batch_69f7064e906881909c3186c646145d34 |
completed | May 3, 2026, 8:24 a.m. |
| PD | Predicate disambiguation | batch_69f70100ec1c8190a6b97f50e88891f2 |
completed | May 3, 2026, 8:02 a.m. |
Created at: May 1, 2026, 1:50 a.m.