Triple
T36781730
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Operation Isotope |
E908785
|
entity |
| Predicate | legalOutcomeForCapturedHijackers |
P201191
|
FINISHED |
| Object | tried in Israel |
—
|
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: tried in Israel | Statement: [Operation Isotope, legalOutcomeForCapturedHijackers, tried in Israel]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: legalOutcomeForCapturedHijackers Context triple: [Operation Isotope, legalOutcomeForCapturedHijackers, tried in Israel]
-
A.
hijackingEndedBy
Indicates that a hijacking event is brought to an end or terminated by a specified agent or action.
-
B.
hijacked
Indicates that one entity has forcibly taken control of another entity, typically without authorization and against the will of its rightful controller.
-
C.
numberOfHijackers
Indicates the quantity of individuals who carried out or attempted to carry out a hijacking in the described event or context.
-
D.
hostageOutcome
Indicates the result or final status of a hostage situation, such as whether hostages were released, rescued, harmed, or remained captive.
-
E.
hijackingTimeApproximate
Indicates that the time at which a hijacking occurred is known only approximately rather than as an exact timestamp.
- 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_69f76e798aa08190ace31098d1b13e9f |
completed | May 3, 2026, 3:49 p.m. |
| NER | Named-entity recognition | batch_69ffdd05d1908190957deb11392f4595 |
completed | May 10, 2026, 1:19 a.m. |
| PD | Predicate disambiguation | batch_69ffdc0d33c881908b3483bee8a96540 |
completed | May 10, 2026, 1:14 a.m. |
| PDg | Predicate description generation | batch_69ffdd0486e08190a0f2ff4ce0aee13b |
completed | May 10, 2026, 1:19 a.m. |
Created at: May 3, 2026, 4:12 p.m.