Triple
T3017283
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Malaysia Airlines Flight 370 |
E82366
|
entity |
| Predicate | disappearanceLocationRegion |
P19453
|
FINISHED |
| Object | southern Indian Ocean (inferred) |
—
|
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: southern Indian Ocean (inferred) | Statement: [Malaysia Airlines Flight 370, disappearanceLocationRegion, southern Indian Ocean (inferred)]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: disappearanceLocationRegion Context triple: [Malaysia Airlines Flight 370, disappearanceLocationRegion, southern Indian Ocean (inferred)]
-
A.
placeOfDisappearance
chosen
Indicates the location where an entity was last seen or went missing.
-
B.
mentionsRegion
Indicates that one entity explicitly refers to or cites a specific geographic region in its content or context.
-
C.
landingRegion
Indicates the area or zone where an object or entity comes to rest or makes contact after moving or descending.
-
D.
foundInRegion
Indicates that something is located within, occurs in, or is associated with a specific geographic or spatial region.
-
E.
recipientRegion
Indicates the geographic region that receives or is the destination of a transfer, delivery, or directed action.
- 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_69ad8b1eb53481908c39bbcd1ec104b2 |
completed | March 8, 2026, 2:43 p.m. |
| NER | Named-entity recognition | batch_69ad9a90ea64819080620e60bbd6aa24 |
completed | March 8, 2026, 3:49 p.m. |
| PD | Predicate disambiguation | batch_69ad961a97188190809dc73430a8eda8 |
completed | March 8, 2026, 3:30 p.m. |
Created at: March 8, 2026, 3 p.m.