Triple
T10327854
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Arwen |
E242805
|
entity |
| Predicate | grandmother |
P3524
|
FINISHED |
| Object | Elwing |
E836929
|
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: Elwing | Statement: [Arwen, grandmother, Elwing]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Elwing Context triple: [Arwen, grandmother, Elwing]
-
A.
Elwing
chosen
Elwing is a half-elven figure from J.R.R. Tolkien’s legendarium, known for bearing the Silmaril to her husband Eärendil and thus helping to bring about the War of Wrath and the downfall of Morgoth.
-
B.
Dorimène
Dorimène is a noble lady courted by the pretentious Monsieur Jourdain in Molière’s comedy *Le Bourgeois gentilhomme*.
-
C.
Celebrían
Celebrían is an Elf of Middle-earth, daughter of Galadriel and Celeborn, who becomes the wife of Elrond and mother of Arwen, Elladan, and Elrohir in J.R.R. Tolkien’s legendarium.
-
D.
Arwen
Arwen is an Elven princess of Rivendell in J.R.R. Tolkien's Middle-earth legendarium, renowned for her beauty, wisdom, and pivotal role in the story of The Lord of the Rings.
-
E.
Nienna
Nienna is a compassionate Vala from J.R.R. Tolkien’s legendarium, known as the Lady of Pity and Mourning who teaches wisdom through sorrow and mercy.
- 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_69d381af787481908bc401325c760a88 |
completed | April 6, 2026, 9:49 a.m. |
| NER | Named-entity recognition | batch_69d4d7cf21e08190bf605daeea0d9dcf |
completed | April 7, 2026, 10:09 a.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69d9336139088190bd9ea3e2333c59cb |
completed | April 10, 2026, 5:29 p.m. |
Created at: April 6, 2026, 11:51 a.m.