Triple
T24416430
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Agua Negra Tunnel |
E615595
|
entity |
| Predicate | isBidirectional |
P88544
|
FINISHED |
| Object | yes |
—
|
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: yes | Statement: [Agua Negra Tunnel, isBidirectional, yes]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: isBidirectional Context triple: [Agua Negra Tunnel, isBidirectional, yes]
-
A.
hasBidirectionalClass
Indicates that there is a mutual, two-way class relationship between the involved entities, where each class is related to the other.
-
B.
isBilateral
chosen
Indicates that the relationship or interaction involves two sides, parties, or entities mutually.
-
C.
bidirectionalClass
Indicates that a class participates in a bidirectional relationship, where each related class maintains a reference to the other.
-
D.
isDirection
Indicates that one entity specifies or represents the orientation or course along which another entity moves, points, or is aligned.
-
E.
isOneWay
Indicates that the relationship or action proceeds in only one direction from a source entity to a target entity, without a corresponding reverse relation.
- 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_69e2d7e9bfac8190a748952a90957106 |
completed | April 18, 2026, 1:01 a.m. |
| NER | Named-entity recognition | batch_69f2958645248190a22bd0b8bcc2dfe2 |
completed | April 29, 2026, 11:34 p.m. |
| PD | Predicate disambiguation | batch_69f287cc4fd4819081e93cc638d9512d |
completed | April 29, 2026, 10:35 p.m. |
Created at: April 18, 2026, 2:13 a.m.