Triple
T31641730
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Rogueport Trouble Center |
E807473
|
entity |
| Predicate | hasInGameSign |
P199813
|
FINISHED |
| Object | Trouble Center signboard |
—
|
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: Trouble Center signboard | Statement: [Rogueport Trouble Center, hasInGameSign, Trouble Center signboard]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: hasInGameSign Context triple: [Rogueport Trouble Center, hasInGameSign, Trouble Center signboard]
-
A.
hasSignInventory
Indicates that an entity possesses or is associated with a specific set or collection of signs used within a writing or symbolic system.
-
B.
hasGameTag
Indicates that a game is associated with a particular descriptive tag or category label.
-
C.
hasInGameService
Indicates that one entity provides or is associated with a service that is available or usable within a game environment.
-
D.
hasInGameCategory
Indicates that an in-game item, action, or entity belongs to a specific predefined category within the game’s classification system.
-
E.
hasInGameActivities
Indicates that an entity includes or offers specific activities or actions that can be performed within a game context.
- 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_69f348d9ce58819093ea2da83cbeeec1 |
completed | April 30, 2026, 12:19 p.m. |
| NER | Named-entity recognition | batch_69ff59b33a38819086cc9aa19b81748b |
completed | May 9, 2026, 3:58 p.m. |
| PD | Predicate disambiguation | batch_69ff587758f88190a39c2164341dc554 |
completed | May 9, 2026, 3:53 p.m. |
| PDg | Predicate description generation | batch_69ff59b1e2ac8190bb65529e9dbbb178 |
completed | May 9, 2026, 3:58 p.m. |
Created at: April 30, 2026, 10:49 p.m.