Triple
T37232324
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Thiou@fr |
E923168
|
entity |
| Predicate | lexicalForm |
P187325
|
FINISHED |
| Object | "Thiou" |
—
|
NE NERFINISHED |
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: "Thiou" | Statement: [Thiou@fr, lexicalForm, "Thiou"]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: lexicalForm Context triple: [Thiou@fr, lexicalForm, "Thiou"]
-
A.
standardizedFormOf
Indicates that one entity is the normalized or officially standardized version of another, often consolidating variations or alternative forms into a single canonical form.
-
B.
localFormOf
Indicates that one entity is a localized or region-specific version or variant of another, more general entity.
-
C.
naturalForm
Indicates that one entity is the inherent, unaltered, or original form or state of another entity.
-
D.
logicalForm
Indicates a relationship where an expression is associated with its structured, formal logical representation.
-
E.
realForm
Indicates that one entity is the actual, concrete or physical form or manifestation of another entity (such as an abstract, alternate, or disguised version).
- 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_69f76ea7f0008190b31b8e30f3d05a71 |
completed | May 3, 2026, 3:50 p.m. |
| NER | Named-entity recognition | batch_69fb4134225081909fd60703b8cae397 |
completed | May 6, 2026, 1:25 p.m. |
| PD | Predicate disambiguation | batch_69fb35bf767081908de8345358ca7f44 |
completed | May 6, 2026, 12:36 p.m. |
| PDg | Predicate description generation | batch_69fb41333b548190912cb238ffc271c9 |
completed | May 6, 2026, 1:25 p.m. |
Created at: May 3, 2026, 4:15 p.m.