Triple
T15469189
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Kingdom of Tyre |
E372111
|
entity |
| Predicate | product |
P490
|
FINISHED |
| Object | Tyrian purple |
E164372
|
NE 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: Tyrian purple | Statement: [Kingdom of Tyre, product, Tyrian purple]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Tyrian purple Context triple: [Kingdom of Tyre, product, Tyrian purple]
-
A.
Tyrian purple
chosen
Tyrian purple is a famous ancient royal purple dye, historically prized for its vivid color and rarity, originally produced from sea snails along the Phoenician coast.
-
B.
Ultramarine
Ultramarine is a poetry collection by American writer Raymond Carver that showcases his characteristically spare, emotionally resonant style.
-
C.
Amarantine
Amarantine is a 2005 studio album by Irish singer Enya, known for its ethereal new-age sound and lush, layered vocals.
-
D.
Carmine
Carmine is a given name, often used in Italian and English-speaking contexts, that is related to the name Carmelo.
-
E.
Rose Madder
Rose Madder is a psychological horror novel by Stephen King that follows an abused woman who escapes her violent husband and becomes entangled with a supernatural painting.
- F. None of above.
- G. Unsure - the case is ambiguous/there is not enough information to decide.
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_69d85cc8bd308190886949510b42e764 |
completed | April 10, 2026, 2:13 a.m. |
| NER | Named-entity recognition | batch_69e03f6b49788190b270fdfe92646842 |
completed | April 16, 2026, 1:46 a.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69ff3657972481909219bc040f674c02 |
completed | May 9, 2026, 1:27 p.m. |
Created at: April 10, 2026, 3:33 a.m.