Triple
T9160940
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Ungava Bay |
E219818
|
entity |
| Predicate | marineEcosystemIncludes |
P12485
|
FINISHED |
| Object | seals |
—
|
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: seals | Statement: [Ungava Bay, marineEcosystemIncludes, seals]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: marineEcosystemIncludes Context triple: [Ungava Bay, marineEcosystemIncludes, seals]
-
A.
hasMarineEcosystem
Indicates that an entity possesses, contains, or is associated with a marine ecosystem as part of its characteristics or environment.
-
B.
hasMarineEcoregion
Indicates that an entity is associated with, or located within, a specific marine ecoregion.
-
C.
hasMarineSpecies
chosen
Indicates that an entity contains, supports, or is associated with one or more marine species.
-
D.
marineLifeTrend
Indicates a change over time in the abundance, health, or distribution of marine life populations.
-
E.
hasAquaticEcosystem
Indicates that an entity possesses, contains, or is associated with an ecosystem primarily based in water (such as rivers, lakes, wetlands, or oceans).
- 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_69ca83e3633c81908688a9fa2306ba99 |
completed | March 30, 2026, 2:08 p.m. |
| NER | Named-entity recognition | batch_69ccaa2ac0508190b2f5c801c2c26d66 |
completed | April 1, 2026, 5:16 a.m. |
| PD | Predicate disambiguation | batch_69cc6605c6808190a30d92da006206ac |
completed | April 1, 2026, 12:25 a.m. |
Created at: March 30, 2026, 7:21 p.m.