Triple
T38332214
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Mara River crossing |
E1037851
|
entity |
| Predicate | hazardToAnimals |
P144198
|
FINISHED |
| Object | steep river banks |
—
|
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: steep river banks | Statement: [Mara River crossing, hazardToAnimals, steep river banks]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: hazardToAnimals Context triple: [Mara River crossing, hazardToAnimals, steep river banks]
-
A.
threatToHumans
Indicates that the subject poses or represents a potential danger, harm, or risk to humans.
-
B.
isHazardTo
chosen
Indicates that one entity poses a potential source of danger, harm, or risk to another entity.
-
C.
involvedAnimal
Indicates that an animal participates in, is affected by, or is otherwise directly connected to the event or situation described.
-
D.
animalFate
Indicates the outcome or destiny that befalls an animal, such as what ultimately happens to it or how its life concludes.
-
E.
usesLiveAnimals
Indicates that one entity employs or incorporates live animals in performing an action, service, process, or activity involving another entity.
- 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_69f76e20d65c81909619ac0dd85c56f0 |
completed | May 3, 2026, 3:47 p.m. |
| NER | Named-entity recognition | batch_69fcc7a4d7f881908b43b960911b81e9 |
completed | May 7, 2026, 5:11 p.m. |
| PD | Predicate disambiguation | batch_69fcc589720c819089c8f500fea3c86a |
completed | May 7, 2026, 5:02 p.m. |
Created at: May 3, 2026, 4:30 p.m.