Triple
T29031987
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Realm of Gondor |
E737751
|
entity |
| Predicate | laterRoyalHouse |
P169876
|
FINISHED |
| Object | House of Telcontar |
—
|
NE NERFINISHED |
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: House of Telcontar | Statement: [Realm of Gondor, laterRoyalHouse, House of Telcontar]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: laterRoyalHouse Context triple: [Realm of Gondor, laterRoyalHouse, House of Telcontar]
-
A.
lastRoyalHouseOf
chosen
Indicates that one entity is the final ruling royal house or dynasty associated with another entity, such as a realm, title, or political unit.
-
B.
reigningRoyalHouseOf
Indicates that a particular royal house currently holds the ruling monarchy over a specified realm or country.
-
C.
relatedRoyalHouse
Indicates a relationship where one royal house is historically, genealogically, or politically connected to another royal house.
-
D.
notableRoyalHouse
Indicates that an entity is prominently associated with, or belongs to, a particular royal house or dynasty.
-
E.
royalAssociation
Indicates a relationship in which an entity is connected or linked to royalty, a royal person, or a royal institution.
- 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_69f077ef00fc81909325f084ad37c035 |
completed | April 28, 2026, 9:03 a.m. |
| NER | Named-entity recognition | batch_69fe189fec148190aeef51b417ba15b0 |
completed | May 8, 2026, 5:08 p.m. |
| PD | Predicate disambiguation | batch_69fe17285b0881908de7569d8dbd20bd |
completed | May 8, 2026, 5:02 p.m. |
Created at: April 28, 2026, 9:56 a.m.