Triple
T25336780
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Lacaune sheep |
E635298
|
entity |
| Predicate | tailStatus |
P3547
|
FINISHED |
| Object | undocked tail |
—
|
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: undocked tail | Statement: [Lacaune sheep, tailStatus, undocked tail]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: tailStatus Context triple: [Lacaune sheep, tailStatus, undocked tail]
-
A.
targetsStatus
Indicates that one entity directs its actions or focus toward another entity based on the latter’s current status or condition.
-
B.
titleStatus
Indicates the current legal or administrative state of a title (such as ownership, validity, or processing stage) in relation to an entity or record.
-
C.
laterStatus
Indicates that one entity represents a subsequent or resulting status or condition of another entity in time.
-
D.
tailConfiguration
chosen
Indicates how the tail of an entity is arranged, structured, or positioned relative to the rest of that entity.
-
E.
tailLocation
Indicates the spatial position or placement of an entity’s tail relative to a reference frame or another object.
- 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_69e75a99bd6481909476115b35b9a8e4 |
completed | April 21, 2026, 11:08 a.m. |
| NER | Named-entity recognition | batch_69f498b39adc8190b0fc4925ce0769ed |
completed | May 1, 2026, 12:12 p.m. |
| PD | Predicate disambiguation | batch_69f45d0dbc8c8190beecce679fce90a4 |
completed | May 1, 2026, 7:58 a.m. |
Created at: April 21, 2026, 1:32 p.m.