Triple
T19636447
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Haringvliet estuary |
E471408
|
entity |
| Predicate | isImportantStopoverFor |
P98902
|
FINISHED |
| Object | waterfowl |
—
|
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: waterfowl | Statement: [Haringvliet estuary, isImportantStopoverFor, waterfowl]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: isImportantStopoverFor Context triple: [Haringvliet estuary, isImportantStopoverFor, waterfowl]
-
A.
isStopoverSiteFor
chosen
Indicates that a location serves as a temporary stopping or resting point along the route or journey of another entity.
-
B.
typicalStopoverCity
Indicates that a city commonly serves as an intermediate stop or layover point in a journey between other locations.
-
C.
stopoverAirport
Indicates that an itinerary or flight includes a particular airport as an intermediate stop between the origin and final destination.
-
D.
isMainArrivalPointFor
Indicates that a location serves as the primary arrival point for a given entity or flow of entities.
-
E.
trailStopOn
Indicates that one entity stops or terminates at the endpoint of a trail or path associated with another entity.
- 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_69d8e511f28481909f4bc3ea9191e54a |
completed | April 10, 2026, 11:54 a.m. |
| NER | Named-entity recognition | batch_69e641070528819085663c439f50148e |
completed | April 20, 2026, 3:06 p.m. |
| PD | Predicate disambiguation | batch_69e514e5cb108190ae260e466c447314 |
completed | April 19, 2026, 5:46 p.m. |
Created at: April 10, 2026, 1:44 p.m.