Triple
T12612450
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Havana Tunnel |
E301160
|
entity |
| Predicate | hasLocationRelativeToCity |
P102712
|
FINISHED |
| Object | beneath entrance to Havana Bay |
—
|
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: beneath entrance to Havana Bay | Statement: [Havana Tunnel, hasLocationRelativeToCity, beneath entrance to Havana Bay]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: hasLocationRelativeToCity Context triple: [Havana Tunnel, hasLocationRelativeToCity, beneath entrance to Havana Bay]
-
A.
hasLocationCity
Indicates that an entity is situated in, occurs in, or is associated with a specific city as its location.
-
B.
hasRelativePositionInCity
chosen
Indicates that one entity occupies a specific spatial or positional relationship within the boundaries or layout of a particular city.
-
C.
locationRelativeToLargestCity
Indicates how a place is spatially positioned or oriented in relation to the largest city in a given area or region.
-
D.
hasMouthPositionRelativeToCity
Indicates the spatial position of a river’s mouth in relation to a specified city.
-
E.
displayLocationCity
Indicates the city where something is shown, presented, or made visible.
- 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_69d7bdeaf49c8190b13800111fa77ea3 |
completed | April 9, 2026, 2:55 p.m. |
| NER | Named-entity recognition | batch_69d9559458dc8190bc4d6e697e99d70e |
completed | April 10, 2026, 7:55 p.m. |
| PD | Predicate disambiguation | batch_69d9541894fc8190a0c3706a414279f0 |
completed | April 10, 2026, 7:48 p.m. |
Created at: April 9, 2026, 5:12 p.m.