Triple
T21479710
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Mon Repos turtle rookery |
E529955
|
entity |
| Predicate | alsoHostsSpecies |
P126903
|
FINISHED |
| Object | flatback turtle |
—
|
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: flatback turtle | Statement: [Mon Repos turtle rookery, alsoHostsSpecies, flatback turtle]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: alsoHostsSpecies Context triple: [Mon Repos turtle rookery, alsoHostsSpecies, flatback turtle]
-
A.
hostSpecies
Indicates the species that serves as the host for another organism, agent, or entity.
-
B.
someSpeciesAre
Indicates that at least one member of a specified group or category belongs to, or can be classified as, a particular species.
-
C.
hasCompanionSpecies
chosen
Indicates that one entity is accompanied by, or exists in association with, another entity of a different species.
-
D.
memberSpecies
Indicates that a particular species is a constituent or member of a larger biological or taxonomic group.
-
E.
moreSpeciesIn
Indicates that one location or context contains a greater number of distinct species than another location or context.
- 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_69e0c45acc3881908e38d3f28964152b |
completed | April 16, 2026, 11:13 a.m. |
| NER | Named-entity recognition | batch_69e9ea1b0130819088b8e96ddbb29317 |
completed | April 23, 2026, 9:44 a.m. |
| PD | Predicate disambiguation | batch_69e631ec1d048190b6da97da8222e413 |
completed | April 20, 2026, 2:02 p.m. |
Created at: April 16, 2026, 6:20 p.m.