Triple
T1018887
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | David Greybeard |
E21994
|
entity |
| Predicate | behaviorObserved |
P23475
|
FINISHED |
| Object | using grass stems to fish for termites |
—
|
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: using grass stems to fish for termites | Statement: [David Greybeard, behaviorObserved, using grass stems to fish for termites]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: behaviorObserved Context triple: [David Greybeard, behaviorObserved, using grass stems to fish for termites]
-
A.
observationType
Indicates the specific kind or category of observation being made or recorded in a given context.
-
B.
behaviorNear
Indicates that one entity exhibits a behavior or action in close spatial proximity to another entity.
-
C.
observedVia
Indicates that something is perceived, detected, or measured through a particular medium, instrument, method, or channel.
-
D.
observedFor
Indicates that one entity is monitored, watched, or examined over a period of time for the benefit or analysis of another entity.
-
E.
observedBy
Indicates that an entity is perceived, monitored, or recorded by another entity acting as the observer.
- 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_69a493c68e24819080ed0ee8bcfd5ce0 |
completed | March 1, 2026, 7:30 p.m. |
| NER | Named-entity recognition | batch_69a4b7c6005081909d9e56114c532d14 |
completed | March 1, 2026, 10:03 p.m. |
| PD | Predicate disambiguation | batch_69a4b7238d4c8190b22d6c2ac0ac4911 |
completed | March 1, 2026, 10:01 p.m. |
| PDg | Predicate description generation | batch_69a4b7a0d0308190a00192aa9062bdaa |
completed | March 1, 2026, 10:03 p.m. |
Created at: March 1, 2026, 7:41 p.m.