Triple
T19000213
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Porifera |
E464927
|
entity |
| Predicate | approximateDescribedSpecies |
P132864
|
FINISHED |
| Object | over 8000 |
—
|
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: over 8000 | Statement: [Porifera, approximateDescribedSpecies, over 8000]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: approximateDescribedSpecies Context triple: [Porifera, approximateDescribedSpecies, over 8000]
-
A.
speciesDescription
Indicates a textual description that characterizes or explains the features, traits, or nature of a species.
-
B.
measuredSpecies
Indicates that a particular species is the subject or target of a measurement or observation in a given context.
-
C.
officiallyDescribedAs
Indicates that an entity is formally characterized or defined using a specific description in an official or authoritative context.
-
D.
speciesNumber
Indicates the numerical identifier or count associated with a particular species in a given context.
-
E.
approximateEstimation
chosen
Indicates an estimation relationship where one value or assessment is only roughly or closely, but not exactly, equal to another.
- 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_69d8dd01a56c81909694a128c66b21d7 |
completed | April 10, 2026, 11:20 a.m. |
| NER | Named-entity recognition | batch_69e5d684d37c8190b975f04a47fa7b92 |
completed | April 20, 2026, 7:32 a.m. |
| PD | Predicate disambiguation | batch_69e4a2f88e0c81908cb20f08bf24cd32 |
completed | April 19, 2026, 9:40 a.m. |
Created at: April 10, 2026, 12:01 p.m.