Triple
T32694871
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Maersk Alabama |
E835978
|
entity |
| Predicate | masterDuringHijacking |
P174800
|
FINISHED |
| Object | Richard Phillips |
—
|
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: Richard Phillips | Statement: [Maersk Alabama, masterDuringHijacking, Richard Phillips]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: masterDuringHijacking Context triple: [Maersk Alabama, masterDuringHijacking, Richard Phillips]
-
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.
majorCapturePhase
Indicates a significant or primary stage in a capture process where the main act of seizing, acquiring, or taking control occurs.
-
D.
master
Indicates that one entity has authoritative control, ownership, or primary dominance over another entity or process.
-
E.
pilotHijacker
Indicates that the subject is a pilot who hijacks, or has hijacked, an aircraft.
- 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.