Triple
T33088729
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Convoy PQ 17 |
E846712
|
entity |
| Predicate | survivingShips |
P24302
|
FINISHED |
| Object | 11 merchant ships reached Soviet ports |
—
|
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: 11 merchant ships reached Soviet ports | Statement: [Convoy PQ 17, survivingShips, 11 merchant ships reached Soviet ports]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: survivingShips Context triple: [Convoy PQ 17, survivingShips, 11 merchant ships reached Soviet ports]
-
A.
survivingShipsOfFleet
chosen
Indicates the subset of ships from a given fleet that remain operational or undestroyed after a specific event or period.
-
B.
shipsSunkOrTotalLoss
Indicates that the referenced ships were sunk or otherwise rendered a total loss (permanently unusable).
-
C.
survivorsWhenSunk
Indicates that when an entity (such as a vessel) was sunk, there were survivors from that event.
-
D.
shipSankIn
Indicates that a specific ship sank (was lost or submerged) in a particular location or body of water.
-
E.
shipTypeSunk
Indicates that a particular type of ship has been sunk as a result of some event or action.
- 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_69f3495590dc8190aa04f3dec74ce976 |
completed | April 30, 2026, 12:21 p.m. |
| NER | Named-entity recognition | batch_69f6f38159d08190980ad639e08f00f4 |
completed | May 3, 2026, 7:04 a.m. |
| PD | Predicate disambiguation | batch_69f6e3d7bee48190b94e0beb48a1d7fa |
completed | May 3, 2026, 5:57 a.m. |
Created at: May 1, 2026, 1:26 a.m.