Triple
T15578814
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Shellcreeper |
E374439
|
entity |
| Predicate | stateChange |
P35872
|
FINISHED |
| Object | flipped state when hit from below |
—
|
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: flipped state when hit from below | Statement: [Shellcreeper, stateChange, flipped state when hit from below]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: stateChange Context triple: [Shellcreeper, stateChange, flipped state when hit from below]
-
A.
statusChange
chosen
Indicates a transition in an entity’s state or condition from one status to another over time.
-
B.
stateSetting
Indicates that one entity establishes, configures, or assigns the state or condition of another entity.
-
C.
changedFrom
Indicates that an entity previously had one state, value, or form and was altered or updated from that prior condition to a new one.
-
D.
stateModel
Indicates that an entity is represented or governed by a particular state-based model or state machine.
-
E.
statusChangeRule
Indicates a rule or condition that governs how and when an entity’s status is allowed to change from one state to another.
- 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_69d85ccd575081908909b71a3f3e3a61 |
completed | April 10, 2026, 2:13 a.m. |
| NER | Named-entity recognition | batch_69e04e24064c8190b132c3092877fbfa |
completed | April 16, 2026, 2:49 a.m. |
| PD | Predicate disambiguation | batch_69deda817e9881909b0c66fc9056f7d5 |
completed | April 15, 2026, 12:23 a.m. |
Created at: April 10, 2026, 4:11 a.m.