Triple
T36965304
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Vatra Games |
E914412
|
entity |
| Predicate | partOfSeriesWorkedOn |
P100406
|
FINISHED |
| Object | Silent Hill |
—
|
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: Silent Hill | Statement: [Vatra Games, partOfSeriesWorkedOn, Silent Hill]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: partOfSeriesWorkedOn Context triple: [Vatra Games, partOfSeriesWorkedOn, Silent Hill]
-
A.
workedOnSeries
chosen
Indicates that an entity contributed work to the creation or production of a particular series.
-
B.
worksInSeriesWith
Indicates that one entity collaborates or participates together with another entity within the same series or serialized work.
-
C.
partOfSeriesWith
Indicates that one entity is a member or installment within the same series as another entity, linking them as related parts of a larger sequence or collection.
-
D.
partOfWorkSeriesBy
Indicates that a work is a component or installment within a larger series created by a specific agent (such as an author, artist, or organization).
-
E.
partOfCreativeCommonsReleaseSeries
Indicates that something belongs to or is included within a specific series of releases distributed under a Creative Commons license.
- 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_69f76e8c498c8190b2842db80aea8b3b |
completed | May 3, 2026, 3:49 p.m. |
| NER | Named-entity recognition | batch_6a01378bf05c8190af9f5e06a2810c7d |
completed | May 11, 2026, 1:57 a.m. |
| PD | Predicate disambiguation | batch_6a0137277c6c8190bcec341f2a0757c4 |
completed | May 11, 2026, 1:55 a.m. |
Created at: May 3, 2026, 4:14 p.m.