Triple
T9099312
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | William Legrand |
E218110
|
entity |
| Predicate | treasureFound |
P49926
|
FINISHED |
| Object | Captain Kidd’s buried treasure |
—
|
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: Captain Kidd’s buried treasure | Statement: [William Legrand, treasureFound, Captain Kidd’s buried treasure]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: treasureFound Context triple: [William Legrand, treasureFound, Captain Kidd’s buried treasure]
-
A.
tombDiscovered
Indicates that a tomb has been found or uncovered, typically as the result of exploration, excavation, or chance discovery.
-
B.
wasUncoveredBy
chosen
Indicates that something previously hidden, unknown, or concealed became revealed or discovered through the actions or efforts of a particular agent or process.
-
C.
tressureType
Indicates the specific kind or category of tressure (a heraldic ornamental border around a shield or charge) associated with an entity.
-
D.
goldDiscovered
Indicates that an instance of gold has been found or identified at a particular time, place, or context.
-
E.
operatesOnTreasureIsland
Indicates that an entity conducts business, activities, or operations on Treasure Island.
- 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_69ca83d9844081908e561e367fda6d45 |
completed | March 30, 2026, 2:08 p.m. |
| NER | Named-entity recognition | batch_69cc9710ac04819096b9c8d3399b9c35 |
completed | April 1, 2026, 3:54 a.m. |
| PD | Predicate disambiguation | batch_69cc65fc7f408190a5846e29ab3b97e5 |
completed | April 1, 2026, 12:25 a.m. |
Created at: March 30, 2026, 7:15 p.m.