Triple
T29310225
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Cynodon dactylon |
E743212
|
entity |
| Predicate | dormantAt |
P166829
|
FINISHED |
| Object | cool-season temperatures |
—
|
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: cool-season temperatures | Statement: [Cynodon dactylon, dormantAt, cool-season temperatures]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: dormantAt Context triple: [Cynodon dactylon, dormantAt, cool-season temperatures]
-
A.
isDormant
Indicates that an entity is currently inactive or in a resting state, with its usual functions or activities temporarily suspended.
-
B.
dormancyPeriod
Indicates the length of time an entity remains inactive or in a dormant state before resuming activity.
-
C.
activeAt
Indicates that an entity is functioning, valid, or in effect during a specified time or at a particular location or context.
-
D.
dormantForCenturiesBeforeRecentActivity
Indicates that something remained inactive or unused for several hundred years before showing new or renewed activity in recent times.
-
E.
deactivatedIn
Indicates that an entity has been turned off, disabled, or made inactive within a specified context, system, or time frame.
- 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_69f0912502c8819087d9e8398ee991a8 |
completed | April 28, 2026, 10:51 a.m. |
| NER | Named-entity recognition | batch_69f665e3d30481909b5b20cf5dc252d1 |
completed | May 2, 2026, 9 p.m. |
| PD | Predicate disambiguation | batch_69f660f2e3708190ab658652bcfc04d0 |
completed | May 2, 2026, 8:39 p.m. |
| PDg | Predicate description generation | batch_69f661e9cb308190a56e25dc17df248e |
completed | May 2, 2026, 8:43 p.m. |
Created at: April 28, 2026, 1:16 p.m.