Triple
T1526313
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Homo sapiens |
E32342
|
entity |
| Predicate | isEndemicTo |
P29821
|
FINISHED |
| Object | Earth |
E687
|
NE FINISHED |
How this triple was built (3 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: Earth | Statement: [Homo sapiens, isEndemicTo, Earth]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Earth Context triple: [Homo sapiens, isEndemicTo, Earth]
-
A.
Earth
chosen
Earth is the third planet from the Sun and the only known world to support life, characterized by vast oceans, diverse ecosystems, and a protective atmosphere.
-
B.
Terra
Terra is a sustainability-themed character created as one of the official mascots for Expo 2020 Dubai, symbolizing environmental awareness and ecological responsibility.
-
C.
Mars
Mars is the fourth planet from the Sun, a cold, desert-like world often called the "Red Planet" due to its iron-rich surface and a prime target in the search for past or present extraterrestrial life.
-
D.
The Green Planet
The Green Planet is a BBC nature documentary series that explores the hidden life, behavior, and ecological importance of plants around the world.
-
E.
Mondas
Mondas is the fictional twin planet of Earth in the Doctor Who universe, known as the original home of the Cybermen.
- F. None of above.
- G. Unsure - the case is ambiguous/there is not enough information to decide.
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: isEndemicTo Context triple: [Homo sapiens, isEndemicTo, Earth]
-
A.
hasEndemicSpecies
Indicates that a place or region contains species that are native to and found only within that specific geographic area.
-
B.
isReservoirOf
Indicates that one entity serves as a storage source or container holding a particular substance, resource, or quantity for another entity or purpose.
-
C.
hasEndemismLevel
Indicates the degree to which something is restricted or native to a particular geographic area or region.
-
D.
areEndangeredIn
Indicates that the entities are classified as endangered within a specified geographic area or jurisdiction.
-
E.
wasDiscoveredIn
Indicates that an entity became known or was first identified during a specific time period or at a particular place.
- F. None of above. chosen
Provenance (5 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_69a885e9b0ac819093a9806ad0efc82c |
completed | March 4, 2026, 7:20 p.m. |
| NER | Named-entity recognition | batch_69a933ddc5a881909cdf503f2bc29bd4 |
completed | March 5, 2026, 7:42 a.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69ad2953c5308190984d20f62b7303fd |
completed | March 8, 2026, 7:46 a.m. |
| PD | Predicate disambiguation | batch_69a907ae8f688190ad9000ea1e018585 |
completed | March 5, 2026, 4:33 a.m. |
| PDg | Predicate description generation | batch_69a933dce3488190b20f0e3d37d16371 |
completed | March 5, 2026, 7:42 a.m. |
Created at: March 4, 2026, 7:26 p.m.