Triple
T11983314
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Raya |
E285211
|
entity |
| Predicate | enemy |
P4567
|
FINISHED |
| Object |
Druun
The Druun are malevolent, amorphous spirits from Disney's "Raya and the Last Dragon" that turn living beings to stone and serve as the film’s primary antagonistic force.
|
E958216
|
NE FINISHED |
How this triple was built (4 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: Druun | Statement: [Raya, enemy, Druun]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Druun Context triple: [Raya, enemy, Druun]
-
A.
Drunen
Drunen is a town in the Dutch province of North Brabant, known for its proximity to extensive sand dunes and heathland landscapes.
-
B.
Dargwa
Dargwa is a Northeast Caucasian language spoken primarily by the Dargin people in the Republic of Dagestan, Russia.
-
C.
Andoolo
Andoolo is a small town that serves as an administrative center in the Indonesian province of Southeast Sulawesi.
-
D.
Druj
Druj is a central concept in Iranian mythology, particularly Zoroastrianism, representing cosmic falsehood, deceit, and the destructive forces opposed to truth and order.
-
E.
Gundrak
Gundrak is a troll-themed dungeon instance in World of Warcraft set in the Zul'Drak region of Northrend, featuring the Drakkari empire and their loa gods.
- F. None of above. chosen
- G. Unsure - the case is ambiguous/there is not enough information to decide.
NEDg
Description generation
gpt-5.1
Instruction
Generate a one-sentence description of the target entity. You are given a context triple in the form (subject, predicate, object), where the object is the target entity. # Instructions Use the triple to infer relevant information about the entity. Describe the entity based on what is most defining, well-known. Avoid repeating the information from the triple, unless really essential. # Response Format Return only the sentence: "Description: [one-sentence description of the target entity]"
Input
Entity: Druun Triple: [Raya, enemy, Druun]
Generated description
The Druun are malevolent, amorphous spirits from Disney's "Raya and the Last Dragon" that turn living beings to stone and serve as the film’s primary antagonistic force.
NED2
Entity disambiguation (via description)
gpt-5-mini-2025-08-07
Target entity: Druun Target entity description: The Druun are malevolent, amorphous spirits from Disney's "Raya and the Last Dragon" that turn living beings to stone and serve as the film’s primary antagonistic force.
-
A.
Drunen
Drunen is a town in the Dutch province of North Brabant, known for its proximity to extensive sand dunes and heathland landscapes.
-
B.
Dargwa
Dargwa is a Northeast Caucasian language spoken primarily by the Dargin people in the Republic of Dagestan, Russia.
-
C.
Andoolo
Andoolo is a small town that serves as an administrative center in the Indonesian province of Southeast Sulawesi.
-
D.
Druj
Druj is a central concept in Iranian mythology, particularly Zoroastrianism, representing cosmic falsehood, deceit, and the destructive forces opposed to truth and order.
-
E.
Gundrak
Gundrak is a troll-themed dungeon instance in World of Warcraft set in the Zul'Drak region of Northrend, featuring the Drakkari empire and their loa gods.
- F. None of above. chosen
Provenance (5 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_69d6ab44a77c8190a652f4b27164e4ef |
completed | April 8, 2026, 7:23 p.m. |
| NER | Named-entity recognition | batch_69d903973c848190aac871d6dfecc74b |
completed | April 10, 2026, 2:05 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69f472286edc8190ac72d7dd2b646c91 |
completed | May 1, 2026, 9:28 a.m. |
| NEDg | Description generation | batch_69f47b7c5af08190ab0bff1232530a0c |
completed | May 1, 2026, 10:07 a.m. |
| NED2 | Entity disambiguation (via description) | batch_69f47dd51e648190bddd41766221e22d |
completed | May 1, 2026, 10:17 a.m. |
Created at: April 8, 2026, 9:46 p.m.