Triple
T19883852
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Rosh HaNikra |
E477843
|
entity |
| Predicate | tunnelsPurpose |
P133881
|
FINISHED |
| Object | connect Palestine with Lebanon by rail |
—
|
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: connect Palestine with Lebanon by rail | Statement: [Rosh HaNikra, tunnelsPurpose, connect Palestine with Lebanon by rail]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: tunnelsPurpose Context triple: [Rosh HaNikra, tunnelsPurpose, connect Palestine with Lebanon by rail]
-
A.
tunnels
Indicates that one entity passes through, under, or within another entity via a tunnel-like passage or structure.
-
B.
tunnelType
Indicates the specific kind or classification of a tunnel associated with an entity.
-
C.
numberOfTunnels
Indicates the quantity of tunnels associated with or passing through a given entity or location.
-
D.
usesTunnel
Indicates that one entity makes use of a tunnel as a passage or route to reach or connect to another entity.
-
E.
tunnelConstructionReason
chosen
Indicates the reason or purpose for which a tunnel is being, was, or will be constructed.
- 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_69d8e51f32b08190b3687f4f60353250 |
completed | April 10, 2026, 11:55 a.m. |
| NER | Named-entity recognition | batch_69e6590870908190a18b545f0ff0ccd6 |
completed | April 20, 2026, 4:49 p.m. |
| PD | Predicate disambiguation | batch_69e537e8c4e481909fe95d795b4864e7 |
completed | April 19, 2026, 8:15 p.m. |
Created at: April 10, 2026, 1:52 p.m.