Triple
T2235758
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Lophiiformes |
E49274
|
entity |
| Predicate | bioluminescenceSource |
P37268
|
FINISHED |
| Object | symbiotic bacteria in many deep-sea forms |
—
|
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: symbiotic bacteria in many deep-sea forms | Statement: [Lophiiformes, bioluminescenceSource, symbiotic bacteria in many deep-sea forms]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: bioluminescenceSource Context triple: [Lophiiformes, bioluminescenceSource, symbiotic bacteria in many deep-sea forms]
-
A.
bioluminescent
Indicates that an entity produces and emits light through a biological chemical reaction.
-
B.
lightSourceFor
Indicates that one entity serves as the source of illumination for another entity.
-
C.
hasBioluminescentBay
Indicates that a location possesses a bay where the water naturally emits visible light due to bioluminescent organisms.
-
D.
biota
Indicates the presence or composition of living organisms (flora, fauna, or other life forms) associated with a given entity or environment.
-
E.
biologicalEvent
Indicates a relationship where an entity participates in, causes, or is affected by a process or occurrence in a biological system.
- F. None of above. chosen
Provenance (4 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_69a88aa84bdc819086df50e9c20b301e |
completed | March 4, 2026, 7:40 p.m. |
| NER | Named-entity recognition | batch_69abc093ba0c819091df09a0e018fce1 |
completed | March 7, 2026, 6:07 a.m. |
| PD | Predicate disambiguation | batch_69abbdafc07881909101266a33ae7031 |
completed | March 7, 2026, 5:54 a.m. |
| PDg | Predicate description generation | batch_69abbf9c77fc8190a323bcaf644fb2c5 |
completed | March 7, 2026, 6:03 a.m. |
Created at: March 4, 2026, 7:47 p.m.