Triple
T36961431
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Morph Ovum |
E914316
|
entity |
| Predicate | balanceRole |
P188156
|
FINISHED |
| Object | high-impact crowd-control power-up |
—
|
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: high-impact crowd-control power-up | Statement: [Morph Ovum, balanceRole, high-impact crowd-control power-up]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: balanceRole Context triple: [Morph Ovum, balanceRole, high-impact crowd-control power-up]
-
A.
balanceControl
Indicates the extent to which one entity regulates, maintains, or stabilizes the equilibrium or proportional distribution of another entity or system.
-
B.
balancedAuthorityBetween
Indicates that decision-making power or control is distributed equally or fairly among the involved entities.
-
C.
balancesWith
Indicates that two entities are in a state of equilibrium or mutual offset, such that each counterbalances or matches the other in a specified context.
-
D.
balanceType
Indicates the category or nature of a balance associated with an entity, such as how that balance is classified or treated.
-
E.
balanceDetectedBy
Indicates that the presence or state of balance is identified or measured by a specified detecting entity or method.
- 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_69f76e8c498c8190b2842db80aea8b3b |
completed | May 3, 2026, 3:49 p.m. |
| NER | Named-entity recognition | batch_69fba2877b248190a974eb092243c0c4 |
completed | May 6, 2026, 8:20 p.m. |
| PD | Predicate disambiguation | batch_69fb8d06a1b48190a937aa410d159dfa |
completed | May 6, 2026, 6:48 p.m. |
| PDg | Predicate description generation | batch_69fba28684208190921694f23e350c3b |
completed | May 6, 2026, 8:20 p.m. |
Created at: May 3, 2026, 4:14 p.m.