Triple
T34721098
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Viana do Castelo station |
E1000914
|
entity |
| Predicate | hasAdjacentLineDirection |
P107515
|
FINISHED |
| Object | Porto (southbound) |
—
|
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: Porto (southbound) | Statement: [Viana do Castelo station, hasAdjacentLineDirection, Porto (southbound)]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: hasAdjacentLineDirection Context triple: [Viana do Castelo station, hasAdjacentLineDirection, Porto (southbound)]
-
A.
adjacentLine
Indicates that one line is directly next to another line, sharing a common boundary or position without overlapping.
-
B.
hasAdjacentCodeOnLine
Indicates that one code element is positioned directly next to another on the same line of source code.
-
C.
adjacentLineDirectionSouth
Indicates that one line segment is directly adjacent to another on its southern side or oriented toward the south relative to it.
-
D.
hasAdjacentStationOnLine1
Indicates that one station is directly next to another station along Line 1 in the network.
-
E.
lineDirectionTo
chosen
Indicates the directional relationship from one line to another, such as whether they point in the same, opposite, or a specific relative direction.
- 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_69f76daeb6e48190a4c9a6b0edc80f72 |
completed | May 3, 2026, 3:45 p.m. |
| NER | Named-entity recognition | batch_69fda5003cdc8190a558501271389912 |
completed | May 8, 2026, 8:55 a.m. |
| PD | Predicate disambiguation | batch_69fda05bfc2c819096821a5300e9bb24 |
completed | May 8, 2026, 8:35 a.m. |
Created at: May 3, 2026, 3:59 p.m.