Triple
T33430912
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Action of 22 September 1914 |
E856127
|
entity |
| Predicate | countryOfShipLost |
P156397
|
FINISHED |
| Object | United Kingdom |
—
|
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: United Kingdom | Statement: [Action of 22 September 1914, countryOfShipLost, United Kingdom]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: countryOfShipLost Context triple: [Action of 22 September 1914, countryOfShipLost, United Kingdom]
-
A.
countryOfShipSunk
chosen
Indicates the country to which a ship that was sunk belonged or was registered.
-
B.
countryOfBritishShips
Indicates the country to which British ships belong or are registered.
-
C.
sunkCountry
Indicates that one entity (typically a vessel or force) caused the sinking of a country’s ship(s) or naval assets belonging to another country.
-
D.
hasShipwrecksFrom
Indicates that something contains or is associated with shipwrecks originating from a specified source, location, or time period.
-
E.
homeportCountry
Indicates the country where a vessel is officially registered as its home port.
- 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_69f349709e7881908c342b4d34f555f4 |
completed | April 30, 2026, 12:22 p.m. |
| NER | Named-entity recognition | batch_6a00b479c1588190af6e0698b7f8d7f7 |
completed | May 10, 2026, 4:38 p.m. |
| PD | Predicate disambiguation | batch_6a00b4158260819087d0cfad8b18cef4 |
completed | May 10, 2026, 4:36 p.m. |
Created at: May 1, 2026, 1:36 a.m.