Triple
T33971734
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Madrid–Barcelona |
E871014
|
entity |
| Predicate | segmentOpening |
P141653
|
FINISHED |
| Object | Madrid–Zaragoza 2003 |
—
|
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: Madrid–Zaragoza 2003 | Statement: [Madrid–Barcelona, segmentOpening, Madrid–Zaragoza 2003]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: segmentOpening Context triple: [Madrid–Barcelona, segmentOpening, Madrid–Zaragoza 2003]
-
A.
openedSegment
Indicates that one entity has initiated or created a new segment, section, or interval within another entity or process.
-
B.
openedSegmentBySegment
Indicates that something was opened gradually in distinct parts or stages, rather than all at once.
-
C.
openedFirstSegmentBetween
chosen
Indicates that one entity initiated or created the first segment in a sequence that connects it to another entity.
-
D.
sectionOpened
Indicates that a particular section has been opened or expanded, making its contents visible or active.
-
E.
openedSectionBetween
Indicates that one entity has created or established an open section, gap, or interval between itself and another entity.
- 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_69f3499da0188190ab1a4ff06fb06a2a |
completed | April 30, 2026, 12:22 p.m. |
| NER | Named-entity recognition | batch_69f7064e906881909c3186c646145d34 |
completed | May 3, 2026, 8:24 a.m. |
| PD | Predicate disambiguation | batch_69f70100ec1c8190a6b97f50e88891f2 |
completed | May 3, 2026, 8:02 a.m. |
Created at: May 1, 2026, 1:50 a.m.