Triple
T16817446
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Paris–London high-speed corridor |
E408789
|
entity |
| Predicate | securityCheckLocation |
P40871
|
FINISHED |
| Object | departure stations |
—
|
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: departure stations | Statement: [Paris–London high-speed corridor, securityCheckLocation, departure stations]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: securityCheckLocation Context triple: [Paris–London high-speed corridor, securityCheckLocation, departure stations]
-
A.
securityLocation
chosen
Indicates the place or area where security-related activities, measures, or responsibilities are situated or applied.
-
B.
protectedAtLocation
Indicates that an entity is safeguarded or kept secure at a specific location.
-
C.
positionOnSecurity
Indicates the stance, opinion, or policy an entity holds regarding security-related issues or measures.
-
D.
securityStatus
Indicates the current level or condition of protection, risk, or vulnerability associated with an entity or system.
-
E.
validationLocation
Indicates the place or context where something is checked, confirmed, or verified for correctness or compliance.
- 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_69d88394566c8190b3dcbdc72935f7fa |
completed | April 10, 2026, 4:59 a.m. |
| NER | Named-entity recognition | batch_69e3b2e30cf48190a61936ba0a49df24 |
completed | April 18, 2026, 4:35 p.m. |
| PD | Predicate disambiguation | batch_69e32b814b188190aee525f8779203cd |
completed | April 18, 2026, 6:58 a.m. |
Created at: April 10, 2026, 5:23 a.m.