Triple
T4065401
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Galileo satellite navigation system |
E86311
|
entity |
| Predicate | initialServicesStartDate |
P26318
|
FINISHED |
| Object | 2016-12-15 |
—
|
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: 2016-12-15 | Statement: [Galileo satellite navigation system, initialServicesStartDate, 2016-12-15]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: initialServicesStartDate Context triple: [Galileo satellite navigation system, initialServicesStartDate, 2016-12-15]
-
A.
startDate
Indicates the point in time when an event, state, or relationship begins.
-
B.
firstIntroductionDate
Indicates the date on which an entity was first introduced or presented for the first time.
-
C.
dateOfFirstInternationalService
chosen
Indicates the calendar date on which an entity first began providing international service.
-
D.
beganInYear
Indicates that an event, process, or state started in a specific calendar year.
-
E.
earliestOccupationDate
Indicates the earliest known date on which an entity began a particular occupation or role.
- 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_69aed93c69208190a4efac0efe3cd69b |
completed | March 9, 2026, 2:29 p.m. |
| NER | Named-entity recognition | batch_69aefd0bdea48190805a79515ee92709 |
completed | March 9, 2026, 5:02 p.m. |
| PD | Predicate disambiguation | batch_69aef90438908190a005b08ba271eacf |
completed | March 9, 2026, 4:44 p.m. |
Created at: March 9, 2026, 3:38 p.m.