Triple
T29678814
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Sydney Harbour midget submarine attack |
E750894
|
entity |
| Predicate | numberOfSubmarinesUsed |
P201653
|
FINISHED |
| Object | 3 |
—
|
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: 3 | Statement: [Sydney Harbour midget submarine attack, numberOfSubmarinesUsed, 3]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: numberOfSubmarinesUsed Context triple: [Sydney Harbour midget submarine attack, numberOfSubmarinesUsed, 3]
-
A.
engagedSubmarines
Indicates that one entity took hostile or combat action against submarines belonging to another entity.
-
B.
submarineCapacity
Indicates the maximum number of people or amount of cargo that a submarine is designed or allowed to carry.
-
C.
numberOfWarPatrols
Indicates the count of distinct war patrol missions associated with an entity.
-
D.
numberOfTorpedoesHit
Indicates the number of torpedoes that successfully struck a specified target.
-
E.
numberOfTorpedoesFired
Indicates the quantity of torpedoes that have been launched or discharged in a given context or event.
- 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_69f0d624d7b08190ba237d226f78d0d9 |
completed | April 28, 2026, 3:45 p.m. |
| NER | Named-entity recognition | batch_6a0010e46d948190a51111b5270fade7 |
completed | May 10, 2026, 5 a.m. |
| PD | Predicate disambiguation | batch_6a001061d34c8190bfe73f3d7c061eb7 |
completed | May 10, 2026, 4:58 a.m. |
| PDg | Predicate description generation | batch_6a0010e304a08190a4d0a4fa11a9a3b3 |
completed | May 10, 2026, 5 a.m. |
Created at: April 28, 2026, 7:09 p.m.