Triple
T17085845
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Leptanilloides |
E414594
|
entity |
| Predicate | behaviorSimilarity |
P94757
|
FINISHED |
| Object | army ants |
—
|
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: army ants | Statement: [Leptanilloides, behaviorSimilarity, army ants]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: behaviorSimilarity Context triple: [Leptanilloides, behaviorSimilarity, army ants]
-
A.
hasSimilarityTo
chosen
Indicates that one entity shares common characteristics, features, or qualities with another entity to a notable degree.
-
B.
lessSimilarTo
Indicates that one entity is considered to share fewer similarities or a weaker resemblance with another entity compared to some reference or alternative.
-
C.
similarityReason
Indicates that there is an identified basis or explanation for why two entities are considered similar.
-
D.
behaviorObserved
Indicates that a particular behavior or action has been witnessed, recorded, or detected in relation to an entity or context.
-
E.
trainingModelSimilarTo
Indicates that one training model is similar to another in terms of structure, behavior, or learned characteristics.
- 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_69d886cef44c8190ba56c44b4e863e64 |
completed | April 10, 2026, 5:12 a.m. |
| NER | Named-entity recognition | batch_69e3dbe6d5288190bdaec41c642d52a2 |
completed | April 18, 2026, 7:30 p.m. |
| PD | Predicate disambiguation | batch_69e35d67b14481909fcdbdeaa5c34785 |
completed | April 18, 2026, 10:31 a.m. |
Created at: April 10, 2026, 5:35 a.m.