Triple
T17125123
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Tapinoma sessile |
E415572
|
entity |
| Predicate | infests |
P27264
|
FINISHED |
| Object | residential buildings |
—
|
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: residential buildings | Statement: [Tapinoma sessile, infests, residential buildings]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: infests Context triple: [Tapinoma sessile, infests, residential buildings]
-
A.
parasitizes
Indicates a relationship in which one organism lives on or in another organism, deriving nutrients or benefits at the host’s expense.
-
B.
infectsTissue
Indicates that one entity (typically a pathogen or agent) invades and establishes itself within the tissue of another entity.
-
C.
colonizes
chosen
Indicates that one entity establishes control or settlement over another entity’s territory or domain, often imposing its presence, systems, or influence there.
-
D.
infiltratedBy
Indicates that an entity has been secretly entered, penetrated, or taken over by another entity, typically in a covert or unauthorized manner.
-
E.
invade
Indicates entering another entity’s territory or domain, typically by force or without permission, in order to take control or exert dominance.
- 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_69d886d090cc8190a39cb94992586905 |
completed | April 10, 2026, 5:12 a.m. |
| NER | Named-entity recognition | batch_69e3f025fce481908e261f2e363e14f9 |
completed | April 18, 2026, 8:57 p.m. |
| PD | Predicate disambiguation | batch_69e3830192ac819091344a9e5a36c8c9 |
completed | April 18, 2026, 1:11 p.m. |
Created at: April 10, 2026, 5:36 a.m.