Triple
T32694874
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Maersk Alabama |
E835978
|
entity |
| Predicate | hijackingEndedBy |
P174801
|
FINISHED |
| Object | United States Navy |
—
|
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 States Navy | Statement: [Maersk Alabama, hijackingEndedBy, United States Navy]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: hijackingEndedBy Context triple: [Maersk Alabama, hijackingEndedBy, United States Navy]
-
A.
hijacked
Indicates that one entity has forcibly taken control of another entity, typically without authorization and against the will of its rightful controller.
-
B.
hijackingTimeApproximate
Indicates that the time at which a hijacking occurred is known only approximately rather than as an exact timestamp.
-
C.
hijackerAffiliation
Indicates a relationship in which a hijacker is associated with, belongs to, or acts on behalf of a particular group, organization, or cause.
-
D.
heldByEnd
Indicates that an object or item is being held or supported specifically at one of its ends by an agent or another object.
-
E.
coHijackerWith
Indicates that two or more individuals participated together in the act of hijacking the same target (e.g., vehicle, aircraft, or vessel).
- F. None of above. chosen
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_69f3493323288190a4e88251035fe96e |
completed | April 30, 2026, 12:21 p.m. |
| NER | Named-entity recognition | batch_69f6c81cd47c8190b3b8d476327688b8 |
completed | May 3, 2026, 3:59 a.m. |
| PD | Predicate disambiguation | batch_69f6c3f617c08190a70ba880210f908c |
completed | May 3, 2026, 3:41 a.m. |
| PDg | Predicate description generation | batch_69f6c77500a08190b2bdeca33bd2ac08 |
completed | May 3, 2026, 3:56 a.m. |
Created at: May 1, 2026, 1:10 a.m.