Triple
T2305241
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Mary Pickford |
E51822
|
entity |
| Predicate | hairstyle |
P16252
|
FINISHED |
| Object | ringlet curls |
—
|
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: ringlet curls | Statement: [Mary Pickford, hairstyle, ringlet curls]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: hairstyle Context triple: [Mary Pickford, hairstyle, ringlet curls]
-
A.
hairDetail
chosen
Indicates a relationship that specifies particular characteristics or attributes of an entity’s hair, such as style, color, length, or texture.
-
B.
beardStyle
Indicates the specific style or manner in which an entity’s beard is shaped, groomed, or worn.
-
C.
styleTendsTo
Indicates that one style is generally inclined or likely to develop, appear, or be adopted in the direction of another style.
-
D.
styleInFull
Indicates that something is presented, written, or expressed in its complete, unabbreviated, or fully detailed form.
-
E.
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).
- 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_69a88b0bb30c81908ded03b006d29387 |
completed | March 4, 2026, 7:42 p.m. |
| NER | Named-entity recognition | batch_69abce1f4f0c8190a714e4dcb8449f7e |
completed | March 7, 2026, 7:05 a.m. |
| PD | Predicate disambiguation | batch_69abc58ce2a081908ce2f0cadd92e9f8 |
completed | March 7, 2026, 6:28 a.m. |
Created at: March 4, 2026, 7:49 p.m.