Triple
T38447662
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Doors of Durin |
E906682
|
entity |
| Predicate | inscriptionColor |
P60
|
FINISHED |
| Object | silver |
—
|
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: silver | Statement: [Doors of Durin, inscriptionColor, silver]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: inscriptionColor Context triple: [Doors of Durin, inscriptionColor, silver]
-
A.
signatureColor
Indicates that an entity has a characteristic or defining color that is uniquely or primarily associated with it.
-
B.
colorTincture
Indicates that one entity has a specific heraldic color or tincture applied to it.
-
C.
inscriptionFeature
Indicates that one entity bears or contains an inscribed element or marking that is treated as a notable feature in relation to another entity.
-
D.
inscriptionVariant
Indicates that one inscription is a variant form or version of another inscription, differing in content, wording, or presentation while remaining closely related.
-
E.
colors
chosen
Indicates that one entity assigns, describes, or provides the color or colors of 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_69f76e72878c8190a692836c8b01b58b |
completed | May 3, 2026, 3:49 p.m. |
| NER | Named-entity recognition | batch_69fcce7afcd08190906cc3801152656a |
completed | May 7, 2026, 5:40 p.m. |
| PD | Predicate disambiguation | batch_69fcccf140ec8190862d53388a5f40d7 |
completed | May 7, 2026, 5:33 p.m. |
Created at: May 3, 2026, 4:31 p.m.