Triple
T10991634
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Teichmüller theory |
E259765
|
entity |
| Predicate | hasMainObject |
P11684
|
FINISHED |
| Object | Teichmüller space of a surface |
—
|
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: Teichmüller space of a surface | Statement: [Teichmüller theory, hasMainObject, Teichmüller space of a surface]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: hasMainObject Context triple: [Teichmüller theory, hasMainObject, Teichmüller space of a surface]
-
A.
hasMainReferent
chosen
Indicates that one entity serves as the primary or central referent for another entity within a given context.
-
B.
hasMainArch
Indicates that an entity possesses or features a primary or central arch structure.
-
C.
hasMainBody
Indicates that one entity serves as the primary physical or structural body of another entity.
-
D.
hasMainOrgan
Indicates that an entity possesses a primary or principal organ that plays a central role in its biological or functional system.
-
E.
hasMainSource
Indicates that one entity serves as the primary or principal source or origin for another entity.
- 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_69d6aa8a6a548190a750f944ccdc8064 |
completed | April 8, 2026, 7:20 p.m. |
| NER | Named-entity recognition | batch_69d795d1e918819090c71f5a077fa15a |
completed | April 9, 2026, 12:04 p.m. |
| PD | Predicate disambiguation | batch_69d72e93ac648190b46c5d12bf3eb1e9 |
completed | April 9, 2026, 4:44 a.m. |
Created at: April 8, 2026, 9:24 p.m.