Triple
T36963477
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Dust District |
E914365
|
entity |
| Predicate | hasStealthOpportunities |
P99848
|
FINISHED |
| Object | rooftop routes |
—
|
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: rooftop routes | Statement: [Dust District, hasStealthOpportunities, rooftop routes]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: hasStealthOpportunities Context triple: [Dust District, hasStealthOpportunities, rooftop routes]
-
A.
hasStealthGameplay
chosen
Indicates that the subject involves or supports gameplay mechanics centered around stealth, such as avoiding detection or silently bypassing opponents.
-
B.
isStealthUnit
Indicates that an entity functions as a unit specialized in remaining hidden or undetected from opponents.
-
C.
canInfiltrate
Indicates that one entity has the ability or potential to secretly enter, penetrate, or gain access to another entity or system, typically without detection.
-
D.
canBecomeInvisible
Indicates the ability of an entity to transition from being visible to being unseen or undetectable.
-
E.
hasCloaking
Indicates that an entity possesses or is equipped with a cloaking capability that can conceal or obscure it.
- 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_6a006417d1f4819093b2da02dbf2ab22 |
completed | May 10, 2026, 10:55 a.m. |
| PD | Predicate disambiguation | batch_6a00634a7a748190ac4774493fce3d30 |
completed | May 10, 2026, 10:51 a.m. |
Created at: May 3, 2026, 4:14 p.m.