Triple
T21946521
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | least tern |
E541947
|
entity |
| Predicate | headPattern |
P126435
|
FINISHED |
| Object | black cap with white forehead |
—
|
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: black cap with white forehead | Statement: [least tern, headPattern, black cap with white forehead]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: headPattern Context triple: [least tern, headPattern, black cap with white forehead]
-
A.
headGivesRiseTo
Indicates that one entity (the head) is the source or origin from which another entity arises, develops, or is produced.
-
B.
headType
Indicates the specific kind or category of head associated with an entity (e.g., type of head part, head role, or head classification in a structure or system).
-
C.
hatPattern
Indicates that one entity has a hat characterized by a specific pattern or design.
-
D.
headCondition
chosen
Indicates that an entity has a specific condition, state, or attribute affecting its head.
-
E.
headDescription
Indicates that one entity serves as a textual or semantic description of the head (primary) entity in the relationship.
- 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_69e0c47ef0e48190a50e1bcc43f4b3fd |
completed | April 16, 2026, 11:14 a.m. |
| NER | Named-entity recognition | batch_69f12428dee48190acb63051ed7cd03e |
completed | April 28, 2026, 9:18 p.m. |
| PD | Predicate disambiguation | batch_69e6f5efc208819091ed2cf6841fa600 |
completed | April 21, 2026, 3:58 a.m. |
Created at: April 16, 2026, 7:57 p.m.