Triple
T676430
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Sonoran Desert |
E13086
|
entity |
| Predicate | hasFauna |
P950
|
FINISHED |
| Object | Gila monster |
E32971
|
NE 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: Gila monster | Statement: [Sonoran Desert, hasFauna, Gila monster]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Gila monster Context triple: [Sonoran Desert, hasFauna, Gila monster]
-
A.
Gila monster
chosen
The Gila monster is a large, slow-moving venomous lizard native to the arid regions of the southwestern United States and northwestern Mexico.
-
B.
Mona ground iguana
The Mona ground iguana is a large, critically endangered rock iguana species native only to Mona Island in the Caribbean, known for its rugged habitat and conservation importance.
-
C.
Psammobates
Psammobates is a genus of small, terrestrial tortoises native to arid and semi-arid regions of southern Africa.
-
D.
Echidna
Echidna is a monstrous figure in Greek mythology, often called the "Mother of Monsters," who is typically depicted as half-woman and half-serpent.
-
E.
Goldy Gopher
Goldy Gopher is the costumed gopher character who serves as the energetic and iconic spirit symbol for the University of Minnesota’s athletic teams and campus events.
- F. None of above.
- G. Unsure - the case is ambiguous/there is not enough information to decide.
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_69a4933d3bf88190972041cd8cf143b9 |
completed | March 1, 2026, 7:27 p.m. |
| NER | Named-entity recognition | batch_69a4a04b2ae881908a5c23453bef8572 |
completed | March 1, 2026, 8:23 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69a5dc9f5f7c8190a766c6b545d1abd8 |
completed | March 2, 2026, 6:53 p.m. |
Created at: March 1, 2026, 7:36 p.m.