Triple
T1892935
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Concorde (Air France) |
E41912
|
entity |
| Predicate | firstCommercialServiceDate |
P1929
|
FINISHED |
| Object | 1976-01-21 |
—
|
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: 1976-01-21 | Statement: [Concorde (Air France), firstCommercialServiceDate, 1976-01-21]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: firstCommercialServiceDate Context triple: [Concorde (Air France), firstCommercialServiceDate, 1976-01-21]
-
A.
firstSuccessfulLaunchDate
Indicates the calendar date on which an entity achieved its first successful launch.
-
B.
firstUsedOn
Indicates the date, time, or context in which something was initially applied, activated, or put into use on a particular object or entity.
-
C.
firstCommercialUse
chosen
Indicates the earliest point in time at which something was used commercially or put into commercial operation.
-
D.
dateOfFirstInternationalService
Indicates the calendar date on which an entity first began providing international service.
-
E.
firstProducedAt
Indicates the location or context where something was originally created, manufactured, or brought into existence for the first time.
- 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_69a8864b6de0819098d089f6a1b910a7 |
completed | March 4, 2026, 7:21 p.m. |
| NER | Named-entity recognition | batch_69abb1480a6c81909fcf5cce4c42fed4 |
completed | March 7, 2026, 5:02 a.m. |
| PD | Predicate disambiguation | batch_69abafe7e7e88190b58c0df59187c0c2 |
completed | March 7, 2026, 4:56 a.m. |
Created at: March 4, 2026, 7:34 p.m.