Triple
T15537170
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Green Shell |
E370376
|
entity |
| Predicate | defensiveUse |
P119087
|
FINISHED |
| Object | held behind the kart |
—
|
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: held behind the kart | Statement: [Green Shell, defensiveUse, held behind the kart]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: defensiveUse Context triple: [Green Shell, defensiveUse, held behind the kart]
-
A.
defensiveTactics
Indicates the use or implementation of strategies, maneuvers, or methods intended to protect, guard, or defend against threats or attacks.
-
B.
hasDefensivePurpose
Indicates that something exists or is designed with the primary goal of protection, defense, or safeguarding against threats or harm.
-
C.
usedDefensiveLine
Indicates that an entity employed or deployed a particular defensive line as part of its strategy or actions.
-
D.
defends
Indicates that one entity protects or supports another entity against attack, criticism, or harm.
-
E.
defensiveOperation
Indicates actions or measures undertaken to protect, guard, or defend a target against threats or attacks.
- 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_69d85cc521a08190921fb50319dddc34 |
completed | April 10, 2026, 2:13 a.m. |
| NER | Named-entity recognition | batch_69e0442f3c688190a599165e526af2ed |
completed | April 16, 2026, 2:06 a.m. |
| PD | Predicate disambiguation | batch_69deda7a95c48190bbe29fadcf17191a |
completed | April 15, 2026, 12:23 a.m. |
| PDg | Predicate description generation | batch_69dff7f05f708190850f1d8782e132b0 |
completed | April 15, 2026, 8:41 p.m. |
Created at: April 10, 2026, 4:06 a.m.