Triple
T34797486
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | The Elder Scrolls VI |
E1003130
|
entity |
| Predicate | hasTrailer |
P200415
|
FINISHED |
| Object | E3 2018 teaser trailer |
—
|
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: E3 2018 teaser trailer | Statement: [The Elder Scrolls VI, hasTrailer, E3 2018 teaser trailer]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: hasTrailer Context triple: [The Elder Scrolls VI, hasTrailer, E3 2018 teaser trailer]
-
A.
hasTrailerCar
Indicates that one vehicle is connected to and pulling another vehicle configured as a trailer car.
-
B.
trailerType
Indicates the specific kind or category of trailer associated with or used in relation to an entity.
-
C.
hasTrunk
Indicates that one entity possesses or is equipped with a trunk as a physical feature or component.
-
D.
hasSeparateTrailingTruck
Indicates that an entity is accompanied by a distinct, independently attached trailing truck or carriage rather than having it integrated into its main structure.
-
E.
trailerField
Indicates that one entity is a field or attribute specifically associated with a trailer (such as a trailer record, object, or data structure).
- 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_69f76db543808190b188c6c86a91491b |
completed | May 3, 2026, 3:45 p.m. |
| NER | Named-entity recognition | batch_69ff891e4b9c8190aa86a339a8944496 |
completed | May 9, 2026, 7:21 p.m. |
| PD | Predicate disambiguation | batch_69ff8801180c8190b23e20996ca68e0a |
completed | May 9, 2026, 7:16 p.m. |
| PDg | Predicate description generation | batch_69ff891d54248190be8742197564605a |
completed | May 9, 2026, 7:21 p.m. |
Created at: May 3, 2026, 3:59 p.m.