Triple
T38644992
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Devourer |
E938691
|
entity |
| Predicate | targetRestriction |
P199357
|
FINISHED |
| Object | air units only |
—
|
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 units only | Statement: [Devourer, targetRestriction, air units only]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: targetRestriction Context triple: [Devourer, targetRestriction, air units only]
-
A.
restrictTo
Indicates that one entity limits or confines another entity’s scope, access, or applicability to a specified subset, condition, or context.
-
B.
targetingRule
chosen
Indicates a rule that defines which entities are selected or targeted based on specified conditions or criteria.
-
C.
targetRole
Indicates the specific role or function that an entity is intended or designated to fulfill in a given context.
-
D.
oftenRestrictedTo
Indicates that the use, occurrence, or applicability of something is frequently limited to a particular subset, context, or condition.
-
E.
fieldRestriction
Indicates that access to or use of a particular field, area, or domain is limited or constrained by specified rules or conditions.
- 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_69f76ed948ec81908ce7811608a8f359 |
completed | May 3, 2026, 3:50 p.m. |
| NER | Named-entity recognition | batch_69ff6c061c6c81909ff485e9cafc88a2 |
completed | May 9, 2026, 5:16 p.m. |
| PD | Predicate disambiguation | batch_69ff6aaf886c8190a3c87d089453f3de |
completed | May 9, 2026, 5:11 p.m. |
Created at: May 3, 2026, 4:32 p.m.