Triple
T35013005
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Dragonstar |
E1009980
|
entity |
| Predicate | mentionedInGame |
P182007
|
FINISHED |
| Object | The Elder Scrolls III: Morrowind |
—
|
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: The Elder Scrolls III: Morrowind | Statement: [Dragonstar, mentionedInGame, The Elder Scrolls III: Morrowind]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: mentionedInGame Context triple: [Dragonstar, mentionedInGame, The Elder Scrolls III: Morrowind]
-
A.
mentionedInFilm
Indicates that an entity is referenced or talked about within the content of a film.
-
B.
appearedInVideoGame
Indicates that an entity is featured as a character, element, or content within a specific video game.
-
C.
mentionedInParva
Indicates that something is referenced or discussed within a specific parva (section or book) of a larger text.
-
D.
performedInGame
Indicates that an action or event was carried out during a particular game or match.
-
E.
playInGameIntroduced
Indicates that an entity participates as a playable element within the specific game in which it was first introduced.
- 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_69f76dcc3ac8819096a3ed52f5fa2523 |
completed | May 3, 2026, 3:46 p.m. |
| NER | Named-entity recognition | batch_69f7865578d48190bf90e470634fd97d |
completed | May 3, 2026, 5:31 p.m. |
| PD | Predicate disambiguation | batch_69f7841812f081909d878955d114088e |
completed | May 3, 2026, 5:21 p.m. |
| PDg | Predicate description generation | batch_69f78575917481909a3defd6a4c366bd |
completed | May 3, 2026, 5:27 p.m. |
Created at: May 3, 2026, 4:01 p.m.