Triple
T10413246
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | EgyptAir Flight 990 |
E245447
|
entity |
| Predicate | crashLocationRelative |
P87739
|
FINISHED |
| Object | south of Nantucket Island, Massachusetts |
—
|
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: south of Nantucket Island, Massachusetts | Statement: [EgyptAir Flight 990, crashLocationRelative, south of Nantucket Island, Massachusetts]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: crashLocationRelative Context triple: [EgyptAir Flight 990, crashLocationRelative, south of Nantucket Island, Massachusetts]
-
A.
binaryLocation
Indicates that one entity is the physical or logical location where another binary or executable artifact resides.
-
B.
associatedCrashSite
chosen
Indicates that an entity is linked or related to a particular crash site, typically as the site where an incident involving that entity occurred or is recorded.
-
C.
frameLocation
Indicates that one entity serves as the spatial or contextual frame of reference within which another entity is located or interpreted.
-
D.
trapLocation
Indicates the specific place or area where a trap is set, located, or expected to be found.
-
E.
stackLocation
Indicates the position or placement of an item within a stack or layered arrangement.
- 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_69d381be340c8190b05998703d42d224 |
completed | April 6, 2026, 9:49 a.m. |
| NER | Named-entity recognition | batch_69d4ea0ec6fc8190a71af759226a3cba |
completed | April 7, 2026, 11:27 a.m. |
| PD | Predicate disambiguation | batch_69d4dfb6f160819090040644a12395ec |
completed | April 7, 2026, 10:43 a.m. |
Created at: April 6, 2026, 12:10 p.m.