Triple
T1799105
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Airbus A350 |
E39672
|
entity |
| Predicate | firstDeliveryDate |
P32026
|
FINISHED |
| Object | 2014-12-22 |
—
|
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: 2014-12-22 | Statement: [Airbus A350, firstDeliveryDate, 2014-12-22]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: firstDeliveryDate Context triple: [Airbus A350, firstDeliveryDate, 2014-12-22]
-
A.
peakDeliveryTime
Indicates the time period during which deliveries are expected to be at their highest volume or frequency.
-
B.
deliveryDays
Indicates the number of days required for an item or service to be delivered from the sender to the recipient.
-
C.
deliveredAt
Indicates the specific time or location at which something (such as a message, product, or service) is delivered.
-
D.
deliveredDuring
Indicates that one entity was delivered within the time span defined by another entity or temporal interval.
-
E.
deliveryGuarantee
Indicates that one party commits to ensuring that an item, service, or outcome will be delivered under specified conditions or within a defined timeframe.
- 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_69a88632aa588190ba3978fde0db5bbd |
completed | March 4, 2026, 7:21 p.m. |
| NER | Named-entity recognition | batch_69ab61b6ea188190aab9fb839bf1e367 |
completed | March 6, 2026, 11:22 p.m. |
| PD | Predicate disambiguation | batch_69aa61d2f7a8819090301f92d3e358c7 |
completed | March 6, 2026, 5:10 a.m. |
| PDg | Predicate description generation | batch_69ab61b5c8988190bb2b46182a4eb5b4 |
completed | March 6, 2026, 11:22 p.m. |
Created at: March 4, 2026, 7:32 p.m.