Triple
T15550432
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | LZ 37 |
E370727
|
entity |
| Predicate | wasShotDownIn |
P43714
|
FINISHED |
| Object | air combat |
—
|
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: air combat | Statement: [LZ 37, wasShotDownIn, air combat]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: wasShotDownIn Context triple: [LZ 37, wasShotDownIn, air combat]
-
A.
shotDownOver
chosen
Indicates that one entity caused another (typically an aircraft or projectile) to be brought down while it was in flight above a particular location or area.
-
B.
shotDownDate
Indicates the date on which an entity was shot down, such as an aircraft or missile being brought down from the air.
-
C.
tookHeavyDamageAt
Indicates that an entity experienced severe or substantial damage at a specific location or point in time.
-
D.
laterBlownUpTo
Indicates that one entity is subsequently destroyed or blown up at a later time relative to another referenced event or state.
-
E.
killedOnGround
Indicates that one entity caused the death of another entity while the victim was on the ground.
- 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_69d85cc6cf40819091f4a5facee1ebe6 |
completed | April 10, 2026, 2:13 a.m. |
| NER | Named-entity recognition | batch_69e04a93121881909d88ca55a39252ac |
completed | April 16, 2026, 2:33 a.m. |
| PD | Predicate disambiguation | batch_69deda7a95c48190bbe29fadcf17191a |
completed | April 15, 2026, 12:23 a.m. |
Created at: April 10, 2026, 4:08 a.m.