Triple
T24116893
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Coorong Lagoon |
E597538
|
entity |
| Predicate | isLong |
P71793
|
FINISHED |
| Object | true |
—
|
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: true | Statement: [Coorong Lagoon, isLong, true]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: isLong Context triple: [Coorong Lagoon, isLong, true]
-
A.
isLongWhen
Indicates that something has a relatively great length or duration when a specified condition or context holds.
-
B.
hasLong
Indicates that an entity possesses or exhibits a great extent or duration in some measurable dimension (such as length or time).
-
C.
isLongOnlyEligible
Indicates that an entity is permitted to take only long (buy) positions and is not allowed to establish short (sell) positions.
-
D.
isLongRunning
Indicates that an action, process, or operation continues for an extended duration, typically longer than is usual or expected.
-
E.
hasLongStretchIn
chosen
Indicates that something extends for a considerable or continuous distance within a specified area, medium, or context.
- 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_69e288c74200819098ab875b592cb39f |
completed | April 17, 2026, 7:23 p.m. |
| NER | Named-entity recognition | batch_69f1dedf824081908de34db4ced62c13 |
completed | April 29, 2026, 10:35 a.m. |
| PD | Predicate disambiguation | batch_69f17651458c8190bbfd301883e46085 |
completed | April 29, 2026, 3:09 a.m. |
Created at: April 17, 2026, 11:04 p.m.