Triple
T7455165
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Rakhigarhi |
E172103
|
entity |
| Predicate | hasPart |
P35
|
FINISHED |
| Object | mound RGR-5 |
E665291
|
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: mound RGR-5 | Statement: [Rakhigarhi, hasPart, mound RGR-5]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: mound RGR-5 Context triple: [Rakhigarhi, hasPart, mound RGR-5]
-
A.
mound RGR-2
chosen
Mound RGR-2 is one of the principal archaeological mounds at the Indus Valley Civilization site of Rakhigarhi in Haryana, India, containing important remains from this ancient urban settlement.
-
B.
Mound
Mound is a small lakeside city in Minnesota known for its location on the shores of Lake Minnetonka.
-
C.
M-52
M-52 is a state highway in Michigan that runs north–south through several counties, serving as an important regional route for local and through traffic.
-
D.
M-153
M-153 is a state trunkline highway in Michigan, commonly known as Ford Road, that serves as a major east–west arterial route through the Detroit metropolitan area.
-
E.
M51 Isherman
The M51 Isherman is an Israeli-upgraded version of the Sherman tank, fitted with a powerful 105 mm gun and modernized systems for improved performance in mid-20th-century conflicts.
- 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_69c68a66554c8190add75c65942c0317 |
completed | March 27, 2026, 1:47 p.m. |
| NER | Named-entity recognition | batch_69c6f3addd648190b618bfbffe08db2c |
completed | March 27, 2026, 9:16 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69c83c5bab90819093431470e0e8c0e3 |
completed | March 28, 2026, 8:38 p.m. |
Created at: March 27, 2026, 3:15 p.m.