Triple
T26841649
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Maribyrnong |
E675792
|
entity |
| Predicate | safeOrMarginalStatus |
P116325
|
FINISHED |
| Object | Safe Labor seat |
—
|
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: Safe Labor seat | Statement: [Maribyrnong, safeOrMarginalStatus, Safe Labor seat]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: safeOrMarginalStatus Context triple: [Maribyrnong, safeOrMarginalStatus, Safe Labor seat]
-
A.
safeOrMarginal
chosen
Indicates that the relationship or condition is classified as either clearly safe or only marginally acceptable, but not unsafe.
-
B.
safeHarborStatus
Indicates that an entity is protected from certain legal, regulatory, or policy liabilities or penalties when specific qualifying conditions are met.
-
C.
possibleStatus
Indicates the set of statuses that an entity is allowed or able to assume within a given context.
-
D.
regulatedStatusOf
Indicates that one entity has regulatory authority or control over the status or condition of another entity.
-
E.
statusQualifier
Indicates a modifier that refines or specifies the exact nature, condition, or context of a given status.
- 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_69eee9b8d5e88190a07d3455c0fbb21f |
completed | April 27, 2026, 4:44 a.m. |
| NER | Named-entity recognition | batch_69f61b480c2c8190b68fc18091f8e401 |
completed | May 2, 2026, 3:42 p.m. |
| PD | Predicate disambiguation | batch_69f611ad2eb48190ac1ed0090f13f7a9 |
completed | May 2, 2026, 3:01 p.m. |
Created at: April 27, 2026, 5:08 a.m.