Triple
T29100716
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Like a Dragon |
E736633
|
entity |
| Predicate | originalSeriesName |
P90015
|
FINISHED |
| Object | Yakuza |
—
|
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: Yakuza | Statement: [Like a Dragon, originalSeriesName, Yakuza]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: originalSeriesName Context triple: [Like a Dragon, originalSeriesName, Yakuza]
-
A.
originalSeries
chosen
Indicates that one creative work is the initial or primary series from which another related work (such as a sequel, spin-off, or adaptation) originates.
-
B.
firstOngoingSeriesTitle
Indicates that the object is the title of the first ongoing series associated with the subject.
-
C.
primarySeriesNameAtInception
Indicates the name of the primary series as it was at the time the series was first created or introduced.
-
D.
originalTitleName
Indicates that one entity is the original or primary title name associated with another entity.
-
E.
firstSeriesTitle
Indicates the title of the first series in which the subject (such as a work, character, or franchise) appears or to which it belongs.
- 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_69f077ec765c81909474c88bcc8bab43 |
completed | April 28, 2026, 9:03 a.m. |
| NER | Named-entity recognition | batch_69ff519b65f081909902ba83b775ef85 |
completed | May 9, 2026, 3:24 p.m. |
| PD | Predicate disambiguation | batch_69ff506fccdc8190bd93269589040aed |
completed | May 9, 2026, 3:19 p.m. |
Created at: April 28, 2026, 11:11 a.m.