Triple
T16835378
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Joint Investigation Team (MH17) |
E409261
|
entity |
| Predicate | investigatesIncident |
P92831
|
FINISHED |
| Object | downing of Malaysia Airlines Flight 17 |
—
|
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: downing of Malaysia Airlines Flight 17 | Statement: [Joint Investigation Team (MH17), investigatesIncident, downing of Malaysia Airlines Flight 17]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: investigatesIncident Context triple: [Joint Investigation Team (MH17), investigatesIncident, downing of Malaysia Airlines Flight 17]
-
A.
investigatedEvent
Indicates that an event was the subject of an investigation or inquiry carried out by some agent.
-
B.
investigatesCase
chosen
Indicates that one entity conducts an investigation into a particular case involving events, issues, or individuals.
-
C.
investigatedBy
Indicates that an entity is the subject of an investigation carried out by another entity.
-
D.
investigatedFor
Indicates that an entity is the subject of an investigation concerning a suspected involvement in another entity (typically a crime, incident, or wrongdoing).
-
E.
helpsInvestigate
Indicates that one entity assists another entity in carrying out an investigation or inquiry.
- 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_69d883952b048190887740a980b712ed |
completed | April 10, 2026, 4:59 a.m. |
| NER | Named-entity recognition | batch_69e3b31aa44c8190b4f402f1898e6998 |
completed | April 18, 2026, 4:36 p.m. |
| PD | Predicate disambiguation | batch_69e32b87b4248190aaddb05e88452356 |
completed | April 18, 2026, 6:58 a.m. |
Created at: April 10, 2026, 5:23 a.m.