Triple
T27233907
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Captain Haddock |
E682224
|
entity |
| Predicate | comicSeriesOrigin |
P162525
|
FINISHED |
| Object | Belgium |
—
|
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: Belgium | Statement: [Captain Haddock, comicSeriesOrigin, Belgium]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: comicSeriesOrigin Context triple: [Captain Haddock, comicSeriesOrigin, Belgium]
-
A.
comicBookUniverse
Indicates that multiple comic book characters, stories, or events exist within and are governed by the same fictional continuity or shared narrative world.
-
B.
seriesOrigin
Indicates that one entity is the original source or starting point from which a series or sequence of related entities is derived.
-
C.
televisionSeriesOrigin
Indicates the country, region, or place where a television series was originally produced or created.
-
D.
appearsInSeriesByPublisher
Indicates that an entity appears in a series that is produced or released by a specified publisher.
-
E.
mainSeriesFirstAppearance
Indicates the work or installment in which an entity first appears within the primary or main series continuity.
- 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.