Triple
T15017305
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Ras Shamra tablets |
E377988
|
entity |
| Predicate | signFunction |
P74189
|
FINISHED |
| Object | alphabetic signs |
—
|
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: alphabetic signs | Statement: [Ras Shamra tablets, signFunction, alphabetic signs]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: signFunction Context triple: [Ras Shamra tablets, signFunction, alphabetic signs]
-
A.
signText
Indicates that a sign bears or displays a particular textual content.
-
B.
signType
chosen
Indicates the specific category or kind of sign involved in the relationship or action.
-
C.
signGivenBy
Indicates that a sign (such as a signal, gesture, or indication) is produced or provided by one entity to another.
-
D.
signAssociated
Indicates that one entity is associated with, represented by, or linked to a particular sign or symbol of another entity.
-
E.
signature
Indicates that one entity has provided an official or personal signed endorsement, authorization, or acknowledgment on or 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_69d85cd3a3c881908c71fc424d459c17 |
completed | April 10, 2026, 2:13 a.m. |
| NER | Named-entity recognition | batch_69ded7633fcc8190b2231f43252bc46f |
completed | April 15, 2026, 12:10 a.m. |
| PD | Predicate disambiguation | batch_69de9a67cbc481909c19c2de57de4eb7 |
completed | April 14, 2026, 7:50 p.m. |
Created at: April 10, 2026, 2:55 a.m.