Triple
T12221695
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Turnagain Arm |
E291232
|
entity |
| Predicate | boreTideDirection |
P86649
|
FINISHED |
| Object | travels from mouth toward head of the arm |
—
|
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: travels from mouth toward head of the arm | Statement: [Turnagain Arm, boreTideDirection, travels from mouth toward head of the arm]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: boreTideDirection Context triple: [Turnagain Arm, boreTideDirection, travels from mouth toward head of the arm]
-
A.
tideType
Indicates the specific category or phase of the tide (such as high, low, rising, or falling) associated with a given tidal event or condition.
-
B.
tidalCurrentCharacteristic
chosen
Indicates the specific properties or behavior of a tidal current, such as its strength, direction, or variability.
-
C.
waveDirection
Indicates the direction in which a wave is propagating or traveling relative to a reference frame.
-
D.
waterwayDirection
Indicates the directional flow or orientation of a waterway relative to a reference point or path.
-
E.
windDirectionAtLandfall
Indicates the direction from which the wind is blowing at the moment and location where a storm makes landfall.
- 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_69d6ab668acc8190963ba424049d6aee |
completed | April 8, 2026, 7:24 p.m. |
| NER | Named-entity recognition | batch_69d920e312708190b4aede2e21f5f697 |
completed | April 10, 2026, 4:10 p.m. |
| PD | Predicate disambiguation | batch_69d91c3d669c81908eea7ad61122d275 |
completed | April 10, 2026, 3:50 p.m. |
Created at: April 8, 2026, 9:51 p.m.