Triple
T12195348
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Ammit |
E290571
|
entity |
| Predicate | bodyPartAssociation |
P14529
|
FINISHED |
| Object | crocodile head |
—
|
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: crocodile head | Statement: [Ammit, bodyPartAssociation, crocodile head]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: bodyPartAssociation Context triple: [Ammit, bodyPartAssociation, crocodile head]
-
A.
associatedBody
chosen
Indicates a relationship where one entity is linked or connected to another entity as its related or corresponding body.
-
B.
losesBodyPart
Indicates that an entity has a body part removed, detached, or otherwise ceases to possess a specific body part.
-
C.
participatingAssociations
Indicates that certain associations are involved as participants in a given activity, event, or relationship.
-
D.
belongsToBody
Indicates that something is a part of, or under the ownership/authority of, a particular body or organization.
-
E.
associatedItem
Indicates that one item is linked or connected to another in a relevant or context-dependent way, without specifying a more precise relationship.
- 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_69d6ab64de5881908d56eb7a75c6cc69 |
completed | April 8, 2026, 7:24 p.m. |
| NER | Named-entity recognition | batch_69d938cd2edc8190b1971349dbc0dee0 |
completed | April 10, 2026, 5:52 p.m. |
| PD | Predicate disambiguation | batch_69d91c38321c819080d500d0d64a04f6 |
completed | April 10, 2026, 3:50 p.m. |
Created at: April 8, 2026, 9:50 p.m.