Triple
T33088478
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Raid on Yarmouth (1914) |
E846707
|
entity |
| Predicate | shipInvolvedAttacker |
P862
|
FINISHED |
| Object | SMS Seydlitz |
—
|
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: SMS Seydlitz | Statement: [Raid on Yarmouth (1914), shipInvolvedAttacker, SMS Seydlitz]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: shipInvolvedAttacker Context triple: [Raid on Yarmouth (1914), shipInvolvedAttacker, SMS Seydlitz]
-
A.
attackedByVessel
Indicates that an entity is the target of an attack carried out by a vessel (such as a ship or boat).
-
B.
shipInvolved
chosen
Indicates that a ship participates in, is associated with, or plays a role in a specified event or situation.
-
C.
shipAttacked
Indicates that one ship has carried out an attack against another ship.
-
D.
commanderOfAttackedShip
Indicates that one entity is the commanding officer of a ship that is the target of an attack.
-
E.
shipTypeInvolved
Indicates that a particular type or class of ship is involved or participates in a specified event, situation, or relationship.
- 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_69f34954d46c8190a04a159cc5f99efd |
completed | April 30, 2026, 12:21 p.m. |
| NER | Named-entity recognition | batch_69f6d6a6b04c8190bee4cf9c00665ef7 |
completed | May 3, 2026, 5:01 a.m. |
| PD | Predicate disambiguation | batch_69f6d27120988190aacec621cf2bf0e8 |
completed | May 3, 2026, 4:43 a.m. |
Created at: May 1, 2026, 1:26 a.m.