Triple
T17125128
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Tapinoma sessile |
E415572
|
entity |
| Predicate | trailBehavior |
P126190
|
FINISHED |
| Object | forms strong foraging trails |
—
|
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: forms strong foraging trails | Statement: [Tapinoma sessile, trailBehavior, forms strong foraging trails]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: trailBehavior Context triple: [Tapinoma sessile, trailBehavior, forms strong foraging trails]
-
A.
trajectoryType
Indicates the kind or pattern of motion an entity follows along its path over time.
-
B.
trailOrientation
Indicates the directional alignment or facing direction of a trail relative to a reference frame or compass directions.
-
C.
compassBehavior
Indicates how a compass responds or is configured to respond under certain conditions or interactions.
-
D.
trailsBehind
Indicates that one entity follows or moves after another, remaining at a distance behind it in space, time, or progress.
-
E.
trailAccess
Indicates that one entity provides permission or a route for another entity to enter, use, or traverse a specific trail or pathway.
- 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_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. |
| PDg | Predicate description generation | batch_69e3873f62108190966c4e741ebd548d |
completed | April 18, 2026, 1:29 p.m. |
Created at: April 10, 2026, 5:36 a.m.