Triple
T27233885
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Captain Haddock |
E682224
|
entity |
| Predicate | usesExpression |
P162524
|
FINISHED |
| Object | Thundering typhoons |
—
|
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: Thundering typhoons | Statement: [Captain Haddock, usesExpression, Thundering typhoons]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: usesExpression Context triple: [Captain Haddock, usesExpression, Thundering typhoons]
-
A.
usedInExpression
Indicates that one entity (typically a term, symbol, or construct) is employed as a component within another entity that represents an expression.
-
B.
usesExpressionSystem
Indicates that one entity employs or relies on a particular expression system (e.g., a biological, genetic, or computational framework) to produce, express, or manipulate another entity.
-
C.
usesTextExpression
Indicates that one entity employs or represents another entity through a textual expression or string-based form.
-
D.
hasExpression
Indicates that an entity displays or possesses a particular facial or emotional expression.
-
E.
isPartOfExpression
Indicates that something functions as a component or constituent element within a larger expression.
- 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_69eefacdad7881908b7bca61c90a1a1e |
completed | April 27, 2026, 5:57 a.m. |
| NER | Named-entity recognition | batch_69f62b9e5ba88190a3c0d46edec7afe7 |
completed | May 2, 2026, 4:51 p.m. |
| PD | Predicate disambiguation | batch_69f623a91b9c8190b2e2fdbc55cb89b6 |
completed | May 2, 2026, 4:17 p.m. |
| PDg | Predicate description generation | batch_69f625402d808190be8279d895d2b27f |
completed | May 2, 2026, 4:24 p.m. |
Created at: April 27, 2026, 9:47 a.m.