Triple
T11144758
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Moria |
E263640
|
entity |
| Predicate | gateInscriptionPhrase |
P65658
|
FINISHED |
| Object | Speak, friend, and enter |
—
|
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: Speak, friend, and enter | Statement: [Moria, gateInscriptionPhrase, Speak, friend, and enter]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: gateInscriptionPhrase Context triple: [Moria, gateInscriptionPhrase, Speak, friend, and enter]
-
A.
signaturePhraseAssociated
Indicates that a characteristic or frequently used phrase is associated with a particular entity as its recognizable or defining expression.
-
B.
hasSignaturePhrase
chosen
Indicates that an entity (such as a person or character) is associated with a distinctive, repeatedly used phrase that is characteristically theirs.
-
C.
mandatesInscription
Indicates that one entity requires or orders that an inscription be made on or associated with another entity.
-
D.
inscriptionBy
Indicates that an inscription was created, written, or carved by a particular agent or entity.
-
E.
inscriptionUsedWith
Indicates that a particular inscription is employed together with, or in association with, another object, tool, or context in which it is applied or interpreted.
- 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_69d6aa9c0ba08190bbd19c217489b755 |
completed | April 8, 2026, 7:21 p.m. |
| NER | Named-entity recognition | batch_69d7e8634d5481909b114d30a542ea3f |
completed | April 9, 2026, 5:56 p.m. |
| PD | Predicate disambiguation | batch_69d75ce104908190b6cc31ef2f67846a |
completed | April 9, 2026, 8:01 a.m. |
Created at: April 8, 2026, 9:28 p.m.