Triple
T10903529
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | RMS Lusitania |
E257506
|
entity |
| Predicate | cargoControversy |
P42781
|
FINISHED |
| Object | allegations of carrying munitions |
—
|
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: allegations of carrying munitions | Statement: [RMS Lusitania, cargoControversy, allegations of carrying munitions]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: cargoControversy Context triple: [RMS Lusitania, cargoControversy, allegations of carrying munitions]
-
A.
controversialBecause
Indicates that one entity is considered controversial specifically due to, or as a result of, its relationship with or association to another entity.
-
B.
controversy
Indicates a situation in which there is active disagreement, dispute, or public debate between parties over a particular issue, action, or claim.
-
C.
controversyType
chosen
Indicates the specific kind or category of controversy associated with an entity or situation.
-
D.
disputeInvolves
Indicates that a particular dispute includes or concerns the specified entities as participants or parties to the conflict.
-
E.
locationOfControversy
Indicates the place or setting where a dispute, debate, or controversy occurs or is centered.
- 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_69d6aa8550c8819095508a2ed9acf3db |
completed | April 8, 2026, 7:20 p.m. |
| NER | Named-entity recognition | batch_69d761a5dffc8190927b0928978646a4 |
completed | April 9, 2026, 8:21 a.m. |
| PD | Predicate disambiguation | batch_69d70d3d69e08190bb369e9a7927142c |
completed | April 9, 2026, 2:21 a.m. |
Created at: April 8, 2026, 9:22 p.m.