Triple
T128319
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Belfast |
E2597
|
entity |
| Predicate | RMS TitanicBuiltAt |
P2012
|
FINISHED |
| Object | Harland and Wolff shipyard |
E14053
|
NE FINISHED |
How this triple was built (3 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: Harland and Wolff shipyard | Statement: [Belfast, RMS TitanicBuiltAt, Harland and Wolff shipyard]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Harland and Wolff shipyard Context triple: [Belfast, RMS TitanicBuiltAt, Harland and Wolff shipyard]
-
A.
Harland and Wolff
chosen
Harland and Wolff is a historic Belfast-based shipbuilding and heavy engineering company best known for constructing famous ocean liners including RMS Titanic.
-
B.
New York Shipbuilding Corporation
New York Shipbuilding Corporation was a major American shipyard based in Camden, New Jersey, known for constructing numerous U.S. Navy warships in the early to mid-20th century.
-
C.
Great Lakes Works
Great Lakes Works is a large integrated steel manufacturing plant in Michigan known for producing flat-rolled steel products for the automotive and other industries.
-
D.
Kawasaki Shipyard, Kobe
Kawasaki Shipyard in Kobe is a major Japanese shipbuilding and heavy industry facility operated by Kawasaki Heavy Industries, historically known for constructing significant naval and commercial vessels.
-
E.
Kure Naval Arsenal
Kure Naval Arsenal was a major Imperial Japanese Navy shipbuilding and armaments facility known for constructing prominent warships and aircraft carriers before and during World War II.
- F. None of above.
- G. Unsure - the case is ambiguous/there is not enough information to decide.
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: RMS TitanicBuiltAt Context triple: [Belfast, RMS TitanicBuiltAt, Harland and Wolff shipyard]
-
A.
dateOfSinking
Indicates the specific calendar date on which an entity (typically a vessel or structure) sank.
-
B.
wasFirstBuiltInYear
Indicates that the initial construction of an entity was completed in a specified year.
-
C.
hullNumber
Indicates the unique identifying number assigned to the hull of a ship or vessel.
-
D.
builtOn
chosen
Indicates that one entity is constructed, developed, or established using another entity as its base, foundation, or underlying platform.
-
E.
placeOfSinking
Indicates the location where an object or entity sank or was submerged.
- F. None of above.
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_69a2520c0f3481908b0ed054a2fca8d0 |
completed | Feb. 28, 2026, 2:25 a.m. |
| NER | Named-entity recognition | batch_69a25763ccf8819094e8dffb2ff98480 |
completed | Feb. 28, 2026, 2:48 a.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69a2a3d5c7bc8190ba8b36db41a1a57f |
completed | Feb. 28, 2026, 8:14 a.m. |
| PD | Predicate disambiguation | batch_69a2564da96c8190aa8204de25229c15 |
completed | Feb. 28, 2026, 2:43 a.m. |
Created at: Feb. 28, 2026, 2:30 a.m.