Triple
T11047037
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Gondor |
E261160
|
entity |
| Predicate | usesScript |
P1587
|
FINISHED |
| Object | Tengwar |
E778894
|
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: Tengwar | Statement: [Gondor, usesScript, Tengwar]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Tengwar Context triple: [Gondor, usesScript, Tengwar]
-
A.
Tengwar
chosen
Tengwar is a fictional script created by J.R.R. Tolkien, most famously used to write various languages of Middle-earth such as Quenya, Sindarin, and Westron.
-
B.
Aurebesh
Aurebesh is the standardized writing system used to represent the Galactic Basic language in the Star Wars universe.
-
C.
Tibirita
Tibirita is a small municipality in the Cundinamarca Department of central Colombia, located in the Andean highlands.
-
D.
Cirth
Cirth is a runic script devised by J.R.R. Tolkien for his Middle-earth legendarium, primarily used to write the Elvish language Sindarin and other tongues.
-
E.
Sindarin
Sindarin is an Elvish language created by J.R.R. Tolkien and widely spoken by characters in his Middle-earth legendarium.
- 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_69d6aa979bdc8190bf0e79104cc098c1 |
completed | April 8, 2026, 7:20 p.m. |
| NER | Named-entity recognition | batch_69d798307da481908996557a73c9b49a |
completed | April 9, 2026, 12:14 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69e3a9fad8248190810e097d148655f5 |
completed | April 18, 2026, 3:57 p.m. |
Created at: April 8, 2026, 9:26 p.m.