Triple
T33706385
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Ulsan |
E863602
|
entity |
| Predicate | hasLargestShipyardOf |
P198766
|
FINISHED |
| Object | Hyundai Heavy Industries Ulsan Shipyard |
—
|
NE NERFINISHED |
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: Hyundai Heavy Industries Ulsan Shipyard | Statement: [Ulsan, hasLargestShipyardOf, Hyundai Heavy Industries Ulsan Shipyard]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: hasLargestShipyardOf Context triple: [Ulsan, hasLargestShipyardOf, Hyundai Heavy Industries Ulsan Shipyard]
-
A.
hasShipyardIn
Indicates that an entity operates or possesses a shipyard located in a specified place.
-
B.
isLargestSeaportOn
Indicates that a seaport is the largest seaport located on a specified geographic feature, such as a coast, island, or body of water.
-
C.
shipyardCountry
Indicates the country in which a given shipyard is located or to which it belongs.
-
D.
isLargestSeaportIn
Indicates that one location is the largest seaport within a specified geographic or political region.
-
E.
largestNavalBaseIn
Indicates that one entity is the largest naval base located within the specified geographic or political region.
- F. None of above. chosen
Provenance (4 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_69f3498844608190bb8f9b14908d2510 |
completed | April 30, 2026, 12:22 p.m. |
| NER | Named-entity recognition | batch_69ff0491409c8190be40f633a58da0b1 |
completed | May 9, 2026, 9:55 a.m. |
| PD | Predicate disambiguation | batch_69ff040bb5cc81909534c7eee85d5e90 |
completed | May 9, 2026, 9:53 a.m. |
| PDg | Predicate description generation | batch_69ff04901ab081908b68563836fcdc99 |
completed | May 9, 2026, 9:55 a.m. |
Created at: May 1, 2026, 1:43 a.m.