Triple
T4170926
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Zorro |
E84559
|
entity |
| Predicate | trademarkAction |
P54500
|
FINISHED |
| Object | carving a Z mark with his sword |
—
|
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: carving a Z mark with his sword | Statement: [Zorro, trademarkAction, carving a Z mark with his sword]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: trademarkAction Context triple: [Zorro, trademarkAction, carving a Z mark with his sword]
-
A.
trademark
Indicates that one entity legally owns and uses a distinctive sign, name, or symbol to identify and distinguish its goods or services from those of others.
-
B.
visualTrademark
Indicates that one entity serves as a visual trademark or logo representing another entity.
-
C.
trademarkOwner
Indicates that one entity legally owns and holds the rights to a particular trademark associated with another entity or product.
-
D.
isTradeNameOf
Indicates that one name is a commercial or brand designation used for a product, substance, or entity that may also have a different generic or formal name.
-
E.
brand
Indicates that one entity is the commercial brand or label under which another entity (such as a product, service, or organization) is marketed or identified.
- 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_69aed932cab48190b80ffe35f7029ae1 |
completed | March 9, 2026, 2:29 p.m. |
| NER | Named-entity recognition | batch_69af02c87cc88190a9ec3712db18a8a7 |
completed | March 9, 2026, 5:26 p.m. |
| PD | Predicate disambiguation | batch_69af018fb0948190a9701b2e8e5d9bac |
completed | March 9, 2026, 5:21 p.m. |
| PDg | Predicate description generation | batch_69af01ee94ec8190aa6dde54d4571c04 |
completed | March 9, 2026, 5:22 p.m. |
Created at: March 9, 2026, 3:45 p.m.