Triple
T35494265
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | SS Empress of Britain (2070) |
E1025811
|
entity |
| Predicate | associatedShipbuilder |
P110278
|
FINISHED |
| Object | John Brown & Company, Clydebank |
E1841466
|
NE 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: John Brown & Company, Clydebank | Statement: [SS Empress of Britain (2070), associatedShipbuilder, John Brown & Company, Clydebank]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: associatedShipbuilder Context triple: [SS Empress of Britain (2070), associatedShipbuilder, John Brown & Company, Clydebank]
-
A.
associatedWithShipbuilder
chosen
Indicates a relationship where an entity is connected or linked in some relevant capacity to a shipbuilder.
-
B.
shipbuilder
Indicates that one entity is the builder or constructor of a ship associated with another entity.
-
C.
hasShipyardIn
Indicates that an entity operates or possesses a shipyard located in a specified place.
-
D.
shipbuilderType
Indicates the specific kind or category of shipbuilder associated with an entity (e.g., by role, specialization, or organizational type).
-
E.
shipyardFormerName
Indicates that a shipyard previously operated under a different name, specifying what that former name was.
- F. None of above.
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_69f76dfc9c60819089c4217d93922615 |
completed | May 3, 2026, 3:47 p.m. |
| NER | Named-entity recognition | batch_6a037c8d06cc8190ab6a5e18d9d2571e |
completed | May 12, 2026, 7:16 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_6a384a2ce6dc8190862796cbbfb59f33 |
completed | June 21, 2026, 8:31 p.m. |
| PD | Predicate disambiguation | batch_6a037a04d8348190a4819666eab42c9b |
completed | May 12, 2026, 7:05 p.m. |
Created at: May 3, 2026, 4:04 p.m.