Triple
T27678224
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | yellow crazy ant |
E697836
|
entity |
| Predicate | antennaMorphology |
P123548
|
FINISHED |
| Object | long antennae |
—
|
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: long antennae | Statement: [yellow crazy ant, antennaMorphology, long antennae]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: antennaMorphology Context triple: [yellow crazy ant, antennaMorphology, long antennae]
-
A.
antennaType
Indicates the specific kind or category of antenna associated with an entity or connection.
-
B.
antennaSegments
chosen
Indicates that one entity has a specified number or type of segmented parts in its antenna structure in relation to another entity.
-
C.
antennaRotation
Indicates the rotational movement or orientation change of an antenna relative to a reference frame or axis.
-
D.
radarAntennaArrangement
Indicates how radar antennas are positioned, configured, or arranged relative to each other or to a platform.
-
E.
notableAntenna
Indicates that an entity possesses an antenna that is particularly significant, prominent, or noteworthy in some relevant context.
- 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_69ef590d458c81909583290c3cd0478b |
completed | April 27, 2026, 12:39 p.m. |
| NER | Named-entity recognition | batch_69f63535773c81908f37b61311643359 |
completed | May 2, 2026, 5:32 p.m. |
| PD | Predicate disambiguation | batch_69f62c1a92648190835a2c5250d8c758 |
completed | May 2, 2026, 4:53 p.m. |
Created at: April 27, 2026, 2:45 p.m.