Triple
T38634619
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Highrise |
E937543
|
entity |
| Predicate | supportsKillstreakUsage |
P191304
|
FINISHED |
| Object | air support killstreaks |
—
|
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: air support killstreaks | Statement: [Highrise, supportsKillstreakUsage, air support killstreaks]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: supportsKillstreakUsage Context triple: [Highrise, supportsKillstreakUsage, air support killstreaks]
-
A.
hasKillstreakSupport
chosen
Indicates that an entity provides or is associated with special support actions or benefits that become available when another entity achieves a killstreak.
-
B.
usesStrikes
Indicates that one entity employs or relies on strikes as a method, tactic, or means to achieve a goal or exert influence over another entity or situation.
-
C.
allowsGiantKillings
Indicates that one entity permits or enables surprising upsets in which a much weaker or lower-ranked entity defeats a much stronger or higher-ranked one.
-
D.
numberOfConfirmedKills
Indicates the total count of individuals that an entity is reported or confirmed to have killed.
-
E.
serviceNumberOfConfirmedKills
Indicates the number of enemy combatants an individual is officially credited with having killed in the course of their service.
- 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_69f76ed5ca3c81909288f61fbf37b359 |
completed | May 3, 2026, 3:50 p.m. |
| NER | Named-entity recognition | batch_6a037c9141dc819098d7fcc36e69882c |
completed | May 12, 2026, 7:16 p.m. |
| PD | Predicate disambiguation | batch_6a037a2026248190b894436a578d79ac |
completed | May 12, 2026, 7:06 p.m. |
Created at: May 3, 2026, 4:32 p.m.